阅读说明：本技术 一种前车紧急切入及时响应的智能检测方法及系统 (Intelligent detection method and system for timely response of emergency cut-in of front vehicle ) 是由 李飘 于晓阳 胡进 赵梓彤 杨帆 于 2021-07-15 设计创作，主要内容包括：本发明公开了一种前车紧急切入及时响应的智能检测方法及系统,该方法包括：通过传感设备获取车道线信息和前方车辆运动状态信息,判断前方车辆所处的车道信息；将传感设备检测到的多个前方车辆依据其与本车的相对纵向距离进行筛选,得到多个危险目标车辆；综合决策出危险目标车辆,并判断危险目标车辆是否有切入意图；对有切入意图的危险目标车辆,根据其运动状态计算出危险目标车辆变换车道标志位以及本车的减速度信息；当危险目标车辆变换车道标志位持续时间达到设定的时间阈值后,向驾驶员发出提示；并对本车进行制动。本发明通过引入危险目标车辆变换车道标志位,实现对减速度逐渐减小的控制,在满足安全的基础上,还提高了舒适性。(The invention discloses an intelligent detection method and system for timely response of emergency cut-in of a front vehicle, wherein the method comprises the following steps: acquiring lane line information and front vehicle motion state information through sensing equipment, and judging lane information of a front vehicle; screening a plurality of front vehicles detected by the sensing equipment according to the relative longitudinal distance between the front vehicles and the vehicle to obtain a plurality of dangerous target vehicles; comprehensively deciding a dangerous target vehicle and judging whether the dangerous target vehicle has a cut-in intention; calculating lane change mark bits of the dangerous target vehicle and deceleration information of the vehicle according to the motion state of the dangerous target vehicle with the cut-in intention; when the duration time of the lane change marker bit of the dangerous target vehicle reaches a set time threshold, a prompt is sent to a driver; and brakes the vehicle. The invention realizes the control of gradually reducing the deceleration by introducing the dangerous target vehicle to change the lane marker, and improves the comfort on the basis of meeting the safety.)

1. An intelligent detection method for timely response of emergency cut-in of a front vehicle is characterized by comprising the following steps:

s1, acquiring lane line information and front vehicle motion state information through sensing equipment, and judging lane information of the front vehicle;

s2, screening a plurality of front vehicles detected by the sensing equipment according to the relative longitudinal distance between the front vehicles and the vehicle according to the lane information of the front vehicles, and preliminarily obtaining a plurality of dangerous target vehicles;

s3, calculating relative transverse/longitudinal distance information, relative transverse/longitudinal speed and safe transverse/longitudinal distance between the dangerous target vehicle of the adjacent lane and the vehicle, comprehensively deciding the dangerous target vehicle, and judging whether the dangerous target vehicle has cut-in intention;

s4, calculating the lane change mark position of the dangerous target vehicle and the deceleration information of the vehicle according to the motion state of the dangerous target vehicle with the cut-in intention; the flag bit is used for representing the size of the cut-in intention of the dangerous target vehicle;

s5, setting a time threshold, and sending a prompt to a driver when the duration of the lane change zone bit of the dangerous target vehicle reaches the set time threshold;

and S6, braking the vehicle through a driving/braking system according to the lane change mark of the dangerous target vehicle and the deceleration information of the vehicle.

2. The method for intelligently detecting the immediate response to the emergency cut-in of the preceding vehicle as claimed in claim 1, wherein the method of step S1 includes two methods:

1) the method comprises the steps of acquiring lane line information through camera identification, and judging lane information where a front vehicle is located by combining with the motion state information of the front vehicle;

2) the lane line information is acquired through V2R, V2I and a high-precision map, the motion state information of the front vehicle is acquired through V2V, and the lane information of the front vehicle is further judged.

3. The intelligent detection method for immediate response to the urgent cut-in of the preceding vehicle as claimed in claim 2, wherein in step S1, the lane line information C0, C1, C2 and C3 are acquired through camera recognition, and the lane information where the preceding vehicle is located, namely the lane center trajectory curve equation f (x), is determined in combination with the motion state information of the preceding vehicle; the concrete formula is as follows:

f(X)＝C₃×X³+C₂×X²+C₁X+C₀

wherein, X is the longitudinal distance from the point on the advancing direction of the vehicle to the camera, and f (X) is the offset distance of the lane line which changes along with X relative to the camera; c0 is lane line position, C1 is heading angle, C2 is lane line curvature, and C3 is the rate of change of lane line curvature with X.

4. The method for intelligently detecting the immediate response to the emergency cut-in of the preceding vehicle as claimed in claim 1, wherein the method of step S2 comprises:

according to the obtained lane information of the front vehicle, namely a lane central track curve equation f (x); substituting the longitudinal distance x (i) of the front vehicle into a lane central track curve equation to obtain a corresponding f (x (i)) value for judging the lane where the front vehicle is located; if the relative transverse distance y (i) between the front vehicle and the host vehicle is greater than (f (x (i)) + C₀ ^L) The front vehicle i is located in the left lane; if y (i) is less than (f (x (i)) + C₀ ^R) The front vehicle i is located in the right lane, C₀ ^LThe left lane line of the main lane, C₀ ^RThe right lane line of the lane; otherwise, the front vehicle i is positioned in the lane, wherein i represents the ID of the front vehicle; and screening out a plurality of dangerous target vehicles according to the longitudinal distances of the vehicles in front of the left lane, the right lane and the lane.

5. The method for intelligently detecting the emergency cut-in and prompt response of the preceding vehicle as claimed in claim 4, wherein in the step S2, the method for determining the relative lateral distance between the preceding vehicle and the own vehicle is as follows:

if the camera can see the complete tail of the front vehicle and has an overlapping rate with the vehicle, the relative transverse distance is the transverse offset distance from the middle point of the tail of the front vehicle to the camera of the vehicle;

if the camera can only see a part of the tail of the front vehicle or the front vehicle has no overlapping rate with the vehicle, the relative transverse distance is the transverse offset distance from the surface of the front vehicle closest to the vehicle or the closest point to the camera of the vehicle.

6. The method for intelligently detecting the immediate response to the emergency cut-in of the preceding vehicle as claimed in claim 1, wherein the method of step S3 comprises:

judging whether the dangerous target vehicles are larger than a relative transverse distance threshold value y0 or not according to relative transverse distance delta y information of the dangerous target vehicles on the adjacent lane and the vehicle based on the obtained dangerous target vehicles, and if the relative transverse distance of the dangerous target vehicles on the adjacent lane is larger than the relative transverse distance threshold value y0, determining that the dangerous target vehicles have no cutting-in intention; if the relative transverse distance of the dangerous target vehicle on the adjacent lane is smaller than the relative transverse distance threshold value y0, the dangerous target vehicle is considered to have the cut-in intention; the relative lateral distance threshold y0 is calculated as:

y0＝d+c△Vy

d is the basic transverse distance between the dangerous target vehicle and the vehicle, c is an adjusting parameter of the relative transverse speed between the dangerous target vehicle and the vehicle, and Δ Vy is the relative transverse speed between the dangerous target vehicle and the vehicle; the basic transverse distance d is a calibration quantity, and the value is calibrated by a real vehicle debugging road test; the adjusting parameter c is a calibration quantity, and the value is calibrated by a real vehicle debugging road test.

7. The method as claimed in claim 1, wherein the method for calculating the lane change flag of the dangerous target vehicle in step S4 comprises:

the calculation formula of the lane change Flag of the dangerous target vehicle is as follows:

Flag＝min(△y/y0,1)

wherein y0 is a relative lateral distance threshold and Δ y is a relative lateral distance; the Flag value ranges from [0,1], and indicates that the front dangerous target vehicle has a strong cut-in intention when the Flag value is 0, and indicates that the front target vehicle has no cut-in intention when the Flag value is 1.

8. The method according to claim 7, wherein the step S4 of calculating deceleration information of the host vehicle comprises:

if the relative longitudinal distance Δ x of the dangerous target vehicle is greater than the relative longitudinal distance threshold value x0, the dangerous target vehicle is considered to be far away from the host vehicle, and is not considered as the dangerous target vehicle at present; if the relative longitudinal distance delta x of the dangerous target vehicle is smaller than the relative longitudinal distance threshold value x0, calculating the expected longitudinal deceleration aexp of the vehicle corresponding to the dangerous target vehicle;

the calculation formula of the deceleration information a of the host vehicle is:

a＝Flag*aexp＝Flag*k*(△x/max(x0,1))

wherein k is a proportionality coefficient obtained by looking up a table according to the relative longitudinal distance with the front vehicle and the expected distance, x0 is a relative longitudinal distance threshold, and Δ x is the relative longitudinal distance.

9. The method as claimed in claim 1, wherein the step S5 for prompting the driver comprises: the driver is prompted by a meter or speaker device.

10. An intelligent detection system for timely response of emergency cut-in of a preceding vehicle is characterized by comprising the following units:

the lane information acquisition unit is used for acquiring lane line information and front vehicle motion state information through the sensing equipment and judging lane information of the front vehicle;

the dangerous target vehicle detection unit is used for screening a plurality of front vehicles detected by the sensing equipment according to the relative longitudinal distance between the front vehicles and the vehicle according to the lane information of the front vehicles, and preliminarily obtaining a plurality of dangerous target vehicles;

the cut-in intention judging unit is used for calculating the relative transverse/longitudinal distance information, the relative transverse/longitudinal speed and the safe transverse/longitudinal distance between the dangerous target vehicle of the adjacent lane and the vehicle, comprehensively deciding the dangerous target vehicle and judging whether the dangerous target vehicle has a cut-in intention;

the lane marker and deceleration calculating unit is used for calculating the lane change marker of the dangerous target vehicle and the deceleration information of the vehicle according to the motion state of the dangerous target vehicle with the cutting-in intention; the flag bit is used for representing the size of the cut-in intention of the dangerous target vehicle;

the early warning unit is used for setting a time threshold value and sending a prompt to a driver when the duration of the lane change marker bit of the dangerous target vehicle reaches the set time threshold value;

and the active control unit is used for braking the vehicle through the driving/braking system according to the lane change mark bit of the dangerous target vehicle and the deceleration information of the vehicle.

Technical Field

The invention relates to the technical field of automatic driving systems, in particular to an intelligent detection method and system for timely response of emergency cut-in of a front vehicle.

Background

In recent years, rapid development and widespread use of internet technology, high-precision maps, and artificial intelligence have promoted the development of automated driving technology. Relevant reports show that the automatic driving technology can reduce 90% of traffic accidents and 70% of travel cost, and is expected to become a next generation computing platform. The automatic driving technology mainly comprises three major links of perception, decision and execution. Firstly, acquiring and processing environmental information and in-vehicle information through sensor equipment such as a camera, a laser radar or a millimeter wave radar; then, decision judgment is carried out according to the acquired information and the intention of the driver, and a corresponding control strategy is made; and finally, the execution system controls the mechanical energy of the vehicle and feeds the mechanical energy back to the bottom layer module to execute tasks, wherein the tasks comprise drive-by-wire acceleration and deceleration, drive-by-wire braking, drive-by-wire steering and the like.

Due to the limited detectable range of the sensing equipment and other reasons, the sensing equipment may not be able to detect the vehicle ahead in time in the scene of emergency cut-in of the vehicle ahead or the like, or the time delay of the detection of the vehicle ahead as the target vehicle is caused to reduce the error recognition rate of the target vehicle, so that the vehicle cannot slow down in time to ensure the safe distance with the vehicle ahead, and the scene has the risk of colliding with the vehicle ahead.

In a cut-in vehicle monitoring method and system (201811634253.9) of the comparison file, a curvature radius of a constant curvature running path of a vehicle is obtained based on motion information of the vehicle, by means of the curvature radius, the motion information of the cut-in vehicle is converted into the coordinate system of the running path with the fixed curvature, so as to obtain the relative movement information of the cut-in vehicle relative to the fixed-curvature running path, when the cut-in vehicle is determined to be in a preset cut-in vehicle position early warning area based on the relative movement information and is a transverse cut-in target vehicle threatening the vehicle, the longitudinal speed of the vehicle is controlled, and the advanced reaction of the cut-in vehicles is realized, so that the risk of collision between the vehicles is greatly reduced, the driving safety and the performances of an automatic emergency braking system and an adaptive cruise system are improved, and the vehicle is suitable for the situation that the vehicle is in a straight track and a curve track.

In this comparison document, it is considered that the host vehicle reduces the risk of collision by controlling the longitudinal speed when the host vehicle enters the host vehicle warning area in space, but it is not considered that the host vehicle has a risk of collision with the cut-in vehicle without time for deceleration when the cut-in vehicle rapidly cuts in, and the comfort of the host vehicle is not good because the deceleration when the host vehicle starts to decelerate is large.

In a scene such as emergency cut-in of a preceding vehicle, the comfort of the vehicle is not good because the sensing equipment may not detect the preceding vehicle in time or the timing of detecting the preceding vehicle as a target vehicle is delayed to reduce the error recognition rate of the target vehicle, so that the vehicle does not slow down in time to ensure the safe distance from the preceding vehicle or the vehicle requests a larger deceleration.

Disclosure of Invention

The invention aims to solve the technical problem of providing an intelligent detection method and system for timely response of emergency cut-in of a front vehicle, which aim to judge the intention of a target vehicle to change lanes based on information such as the motion states of the target vehicle and the vehicle, can perform emergency cut-in early warning and active control on the front vehicle, avoid the risk of collision with the front vehicle and ensure the safety and comfort of the vehicle.

The technical scheme adopted by the invention for solving the technical problems is as follows:

the invention provides an intelligent detection method for timely response of emergency cut-in of a front vehicle, which comprises the following steps:

s1, acquiring lane line information and front vehicle motion state information through sensing equipment, and judging lane information of the front vehicle;

s2, screening a plurality of front vehicles detected by the sensing equipment according to the relative longitudinal distance between the front vehicles and the vehicle according to the lane information of the front vehicles, and preliminarily obtaining a plurality of dangerous target vehicles;

s3, calculating relative transverse/longitudinal distance information, relative transverse/longitudinal speed and safe transverse/longitudinal distance between the dangerous target vehicle of the adjacent lane and the vehicle, comprehensively deciding the dangerous target vehicle, and judging whether the dangerous target vehicle has cut-in intention;

s4, calculating the lane change mark position of the dangerous target vehicle and the deceleration information of the vehicle according to the motion state of the dangerous target vehicle with the cut-in intention; the flag bit is used for representing the size of the cut-in intention of the dangerous target vehicle;

s5, setting a time threshold, and sending a prompt to a driver when the duration of the lane change zone bit of the dangerous target vehicle reaches the set time threshold;

and S6, braking the vehicle through a driving/braking system according to the lane change mark of the dangerous target vehicle and the deceleration information of the vehicle.

Further, the method of step S1 of the present invention includes two methods:

1) the method comprises the steps of acquiring lane line information through camera identification, and judging lane information where a front vehicle is located by combining with the motion state information of the front vehicle;

2) the lane line information is acquired through V2R, V2I and a high-precision map, the motion state information of the front vehicle is acquired through V2V, and the lane information of the front vehicle is further judged.

Further, in step S1, the lane line information C0, C1, C2, and C3 are acquired through camera recognition, and the lane information where the front vehicle is located, that is, the lane center trajectory curve equation f (x), is determined in combination with the motion state information of the front vehicle; the concrete formula is as follows:

f(X)＝C₃×X³+C₂×X²+C₁X+C₀

wherein, X is the longitudinal distance from the point on the advancing direction of the vehicle to the camera, and f (X) is the offset distance of the lane line which changes along with X relative to the camera; c0 is lane line position, C1 is heading angle, C2 is lane line curvature, and C3 is the rate of change of lane line curvature with X.

Further, the method of step S2 of the present invention includes:

according to the obtained lane information of the front vehicle, namely a lane central track curve equation f (x); substituting the longitudinal distance x (i) of the front vehicle into a lane central track curve equation to obtain a corresponding f (x (i)) value for judging the lane where the front vehicle is located; if the relative transverse distance y (i) between the front vehicle and the host vehicle is greater than (f (x (i)) + C₀ ^L) The front vehicle i is located in the left lane; if y (i) is less than (f (x (i)) + C₀ ^R) The front vehicle i is located in the right lane, C₀ ^LThe left lane line of the main lane, C₀ ^RThe right lane line of the lane; otherwise, the front vehicle i is positioned in the lane, wherein i represents the ID of the front vehicle; and screening out a plurality of dangerous target vehicles according to the longitudinal distances of the vehicles in front of the left lane, the right lane and the lane.

Further, in step S2 of the present invention, the method for determining the relative lateral distance between the front vehicle and the host vehicle is:

if the camera can see the complete tail of the front vehicle and has an overlapping rate with the vehicle, the relative transverse distance is the transverse offset distance from the middle point of the tail of the front vehicle to the camera of the vehicle;

if the camera can only see a part of the tail of the front vehicle or the front vehicle has no overlapping rate with the vehicle, the relative transverse distance is the transverse offset distance from the surface of the front vehicle closest to the vehicle or the closest point to the camera of the vehicle.

Further, the method of step S3 of the present invention includes:

judging whether the dangerous target vehicles are larger than a relative transverse distance threshold value y0 or not according to relative transverse distance delta y information of the dangerous target vehicles on the adjacent lane and the vehicle based on the obtained dangerous target vehicles, and if the relative transverse distance of the dangerous target vehicles on the adjacent lane is larger than the relative transverse distance threshold value y0, determining that the dangerous target vehicles have no cutting-in intention; if the relative transverse distance of the dangerous target vehicle on the adjacent lane is smaller than the relative transverse distance threshold value y0, the dangerous target vehicle is considered to have the cut-in intention; the relative lateral distance threshold y0 is calculated as:

y0＝d+c△Vy

d is the basic transverse distance between the dangerous target vehicle and the vehicle, c is an adjusting parameter of the relative transverse speed between the dangerous target vehicle and the vehicle, and Δ Vy is the relative transverse speed between the dangerous target vehicle and the vehicle; the basic transverse distance d is a calibration quantity, and the value is calibrated by a real vehicle debugging road test; the adjusting parameter c is a calibration quantity, and the value is calibrated by a real vehicle debugging road test.

Further, the method for calculating the lane change flag of the dangerous target vehicle in step S4 of the present invention includes:

the calculation formula of the lane change Flag of the dangerous target vehicle is as follows:

Flag＝min(△y/y0,1)

wherein y0 is a relative lateral distance threshold and Δ y is a relative lateral distance; the Flag value ranges from [0,1], and indicates that the front dangerous target vehicle has a strong cut-in intention when the Flag value is 0, and indicates that the front target vehicle has no cut-in intention when the Flag value is 1.

Further, the method of calculating deceleration information of the host vehicle in step S4 of the present invention includes:

if the relative longitudinal distance Δ x of the dangerous target vehicle is greater than the relative longitudinal distance threshold value x0, the dangerous target vehicle is considered to be far away from the host vehicle, and is not considered as the dangerous target vehicle at present; if the relative longitudinal distance delta x of the dangerous target vehicle is smaller than the relative longitudinal distance threshold value x0, calculating the expected longitudinal deceleration aexp of the vehicle corresponding to the dangerous target vehicle;

the calculation formula of the deceleration information a of the host vehicle is:

a＝Flag*aexp＝Flag*k*(△x/max(x0,1))

wherein k is a proportionality coefficient obtained by looking up a table according to the relative longitudinal distance with the front vehicle and the expected distance, x0 is a relative longitudinal distance threshold, and Δ x is the relative longitudinal distance.

Further, the method for giving a prompt to the driver in step S5 of the present invention includes: the driver is prompted by a meter or speaker device.

The invention provides an intelligent detection system for timely response of emergency cut-in of a front vehicle, which comprises the following units:

the lane information acquisition unit is used for acquiring lane line information and front vehicle motion state information through the sensing equipment and judging lane information of the front vehicle;

the dangerous target vehicle detection unit is used for screening a plurality of front vehicles detected by the sensing equipment according to the relative longitudinal distance between the front vehicles and the vehicle according to the lane information of the front vehicles, and preliminarily obtaining a plurality of dangerous target vehicles;

the cut-in intention judging unit is used for calculating the relative transverse/longitudinal distance information, the relative transverse/longitudinal speed and the safe transverse/longitudinal distance between the dangerous target vehicle of the adjacent lane and the vehicle, comprehensively deciding the dangerous target vehicle and judging whether the dangerous target vehicle has a cut-in intention;

the lane marker and deceleration calculating unit is used for calculating the lane change marker of the dangerous target vehicle and the deceleration information of the vehicle according to the motion state of the dangerous target vehicle with the cutting-in intention; the flag bit is used for representing the size of the cut-in intention of the dangerous target vehicle;

the early warning unit is used for setting a time threshold value and sending a prompt to a driver when the duration of the lane change marker bit of the dangerous target vehicle reaches the set time threshold value;

and the active control unit is used for braking the vehicle through the driving/braking system according to the lane change mark bit of the dangerous target vehicle and the deceleration information of the vehicle.

The invention has the following beneficial effects: the method provided by the invention is used for predicting the intention size and the emergency degree of the target vehicle for changing the lane, and can solve the problem that the vehicle is not in time to decelerate to ensure the safe distance with the front vehicle or the vehicle requests larger deceleration because the sensing equipment can not detect the front vehicle in time or the target vehicle error identification rate is reduced to cause the time delay of the detection of the front vehicle as the target vehicle when the front vehicle is in the scene of emergency cut-in and the like. The invention is derived from the fact that when the vehicle is actually driven on the road, the driver can gradually decelerate to ensure safety as the front vehicle cuts into the road, but the front vehicle already cuts into the road and then performs larger deceleration. By introducing the dangerous target vehicle lane change Flag, the deceleration a request of the system is gradually reduced, the effect of operation with an actual driver is achieved, and the comfort of the system is realized on the basis of meeting the safety of the system.

Drawings

The invention will be further described with reference to the accompanying drawings and examples, in which:

FIG. 1 is a system schematic of an embodiment of the present invention;

FIG. 2 is a block diagram of a logic algorithm of an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Example one

The intelligent detection method for the emergency cut-in and timely response of the front vehicle comprises the following steps:

s1, acquiring lane line information and front vehicle motion state information through sensing equipment, and judging lane information of the front vehicle;

s2, screening a plurality of front vehicles detected by the sensing equipment according to the relative longitudinal distance between the front vehicles and the vehicle according to the lane information of the front vehicles, and preliminarily obtaining a plurality of dangerous target vehicles;

s3, calculating relative transverse/longitudinal distance information, relative transverse/longitudinal speed and safe transverse/longitudinal distance between the dangerous target vehicle of the adjacent lane and the vehicle, comprehensively deciding the dangerous target vehicle, and judging whether the dangerous target vehicle has cut-in intention;

s4, calculating the lane change mark position of the dangerous target vehicle and the deceleration information of the vehicle according to the motion state of the dangerous target vehicle with the cut-in intention; the flag bit is used for representing the size of the cut-in intention of the dangerous target vehicle;

s5, setting a time threshold, and sending a prompt to a driver when the duration of the lane change zone bit of the dangerous target vehicle reaches the set time threshold;

and S6, braking the vehicle through a driving/braking system according to the lane change mark of the dangerous target vehicle and the deceleration information of the vehicle.

Example two

As shown in fig. 2, the intelligent detection method for timely response to emergency cut-in of a preceding vehicle according to the embodiment of the present invention includes the following steps:

s1, according to the lane line information C0, C1, C2 and C3 detected by the sensor, the lane information of the front vehicle, namely the lane center track curve equation f (x), is judged according to the information such as the motion state of the front vehicle. The lane line information may be obtained by V2R (Vehicle to Road), V2I (Vehicle to Infrastructure), a high-precision map, and the like, and the information of the moving state of the preceding Vehicle may be obtained by V2V (Vehicle to Vehicle), and the like. The lane line information is mainly obtained by means of recognition of the camera, and coefficients C0, C1, C2 and C3 of a lane center track curve equation can be output when the lane line is recognized through the camera. The lane center track curve equation is:

f(X)＝C₃×X³+C₂×X²+C₁X+C₀

wherein X is the longitudinal distance from a point on the advancing direction of the vehicle to the camera, and the advancing direction of the vehicle is defined as positive; (X) a deviation distance of the lane line relative to the camera which changes with X, and the left direction of the vehicle is defined as positive; c0 is lane line position, f (0) ═ C0, unit m; c1 is heading angle, f' (0) ═ C1, unit rad; c2 is the curvature of lane line, f (2) (0) is 2C2, unit m^-1(ii) a C3 is the rate of change of curvature of lane line with X, and f (3) (0) is 6C3 with m^-2。

The method comprises the following steps that a lane is provided with a left lane line and a right lane line as a standard, and when the lane lines on the two sides are good in quality, the average value of the lane lines on the two sides, namely C0, C1, C2 and C3, is taken as a parameter of a lane center track curve equation; when the quality of only one side lane line is good, taking the side lane lines C1, C2 and C3 as parameters of a lane center track curve equation, and setting C0 as 0; when there is no lane line or the lane line quality is poor, C0, C1, C2, C3 are all 0.

Since C0 represents the lateral distance between the center of the lane line of the own lane and the camera of the own lane, and has an important influence on the determination of the lane where the vehicle ahead is located, C0 and C are described below₀ ^L、C₀ ^RAnd (3) value determination:

if the quality of the lane lines on the two sides is good, the parameter C0 of the curve equation of the lane central track is the left lane line C of the lane₀ ^LAnd the right lane line C of the lane₀ ^RAverage value of (d); when only one side lane line exists, the parameter C0 of the lane center track curve equation is 0, and the parameter C0 of the other side lane line takes the opposite number-C of the lane line₀ ^L/R(ii) a When no lane line or poor lane line quality exists, the C0 parameters of the lane lines on the two sides are C0_ Calib and C0_ Calib (opposite numbers), the variable is a calibration quantity, the value is calibrated by a real vehicle debugging road test, and the range is 2.5-3.75 m (the value is related to factors such as the width of a vehicle and the driving style of a driver).

And S2, screening a plurality of front vehicles detected by the sensing equipment according to the relative longitudinal distance between the front vehicles and the vehicle based on the obtained lane information of the front vehicles, and obtaining a plurality of dangerous target vehicles which are respectively arranged on the left lane, the own lane and the right lane. For example, a plurality of front vehicles detected by the sensing device are screened out to have 6 dangerous target vehicles at most, and the left lane, the own lane and the right lane respectively have 2 dangerous target vehicles at most.

Substituting the longitudinal distance x (i) of the front vehicle into the lane central track curve equation to obtain the corresponding f (x (i)) value for judging the lane where the front vehicle is located. If the relative transverse distance y (i) between the front vehicle and the host vehicle is greater than (f (x (i)) + C₀ ^L) Front vehicleVehicle i is located in the left lane; if y (i) is less than (f (x (i)) + C₀ ^R) The front vehicle i is located in the right lane; otherwise, the front vehicle i is positioned in the lane. Where i represents the ID of the preceding vehicle.

And screening out a plurality of dangerous target vehicles according to the longitudinal distances of the vehicles in front of the left lane, the right lane and the lane.

This car camera is generally installed in front windshield middle department, according to the debugging experience, divides the condition relative lateral distance y: if the camera can see the complete tail of the front vehicle and has an overlapping rate with the vehicle, the relative transverse distance is the transverse offset distance from the middle point of the tail of the front vehicle to the camera of the vehicle; if the camera can only see a part of the tail of the front vehicle or the front vehicle has no overlapping rate with the vehicle, the relative transverse distance is the transverse offset distance from the point of the front vehicle closest to the nearest surface of the vehicle to the camera of the vehicle. However, before this information is used by the actual function, the lateral offset distance is converted into a lateral offset distance between the camera of the host vehicle and the vehicle ahead according to the vehicle width information of the vehicle ahead, and the lateral offset distance is used as the relative lateral distance between the target vehicle and the host vehicle.

This step does not directly use the lateral-longitudinal distance of the vehicle in front to compare with the width of the vehicle itself, mainly for the following reasons: first, the physical information of the vehicle ahead output by the sensor has limited accuracy, and the vehicle cannot be treated as a mass point in the scene of researching the emergency cut-in of the vehicle ahead. Therefore, the vehicle motion information and the lane line information need to be considered comprehensively. On one hand, the stability of the vehicle is improved, and the rapid change of the vehicle motion caused by the small change of the front vehicle is avoided; on the other hand, a plurality of dangerous target vehicles are screened out in advance and then used for subsequent detailed calculation, and the calculation amount in the subsequent steps is reduced.

S3, judging whether the dangerous target vehicles are larger than a relative transverse distance threshold value y0 or not based on the information such as the relative transverse distance Deltay between the dangerous target vehicles and the host vehicle in the adjacent lanes (including the left lane and the right lane) and the like (the obtained dangerous target vehicles are obtained), and comprehensively deciding the information of the dangerous target vehicles by considering the information such as the relative longitudinal distance between the dangerous target vehicles and the host vehicle in the adjacent lanes and the relative speed thereof, wherein if the relative transverse distance between the dangerous target vehicles in the adjacent lanes is larger than the relative transverse distance threshold value y0, the dangerous target vehicles are considered to have no cutting-in intention, if the relative transverse distance between the dangerous target vehicles in the adjacent lanes is smaller than the relative transverse distance threshold value y0, the dangerous target vehicles are considered to have cutting-in intention, and the cutting-in intention evaluation is needed to be carried out on the dangerous target vehicles. the relative transverse distance threshold value y0 has the following calculation formula:

y0＝d+c△Vy

wherein d is the basic transverse distance between the dangerous target vehicle and the host vehicle, c is the adjustment parameter of the relative transverse speed between the dangerous target vehicle and the host vehicle, and Δ Vy is the relative transverse speed between the dangerous target vehicle and the host vehicle.

The basic transverse distance d is a calibration quantity, and the value is calibrated by a real vehicle debugging road test, and the range is 1.0-2.8 m. The adjusting parameter c is a calibration quantity, the value is calibrated by a real vehicle debugging road test, and the physical meaning of the variable is equivalent to the transverse judgment time. The d and c are obtained by combining the speed of the vehicle, the relative speed and the relative longitudinal distance of the dangerous target vehicle and the width of the dangerous target vehicle.

And S4, based on the obtained dangerous target vehicle information, calculating the final acceleration according to the motion state of the dangerous target vehicle, such as the relative transverse and longitudinal distance delta y and delta x, the relative transverse and longitudinal vehicle speed delta Vy and delta Vx, and the like, and carrying out vehicle speed control. If the Δ x of the dangerous target vehicle is greater than the relative longitudinal distance threshold value x0, the dangerous target vehicle is considered to be far away from the host vehicle, and the dangerous target vehicle is not considered at present; if Δ x of the dangerous target vehicle is smaller than the relative longitudinal distance threshold value x0, the expected longitudinal deceleration aexp of the vehicle corresponding to the dangerous target vehicle is obtained.

And determining the intention size of the dangerous target vehicle with the cutting-in intention for changing lanes according to the information such as delta y, y0 and the like based on whether the obtained dangerous target vehicle has the cutting-in intention, and determining the Flag of the dangerous target vehicle for changing lanes and the information of the deceleration a of the vehicle based on the information. The range of the Flag value is [0,1], the Flag value is 0, which indicates that the front dangerous target vehicle has a strong cut-in intention, and the Flag value is 1, which indicates that the front target vehicle has no cut-in intention.

The calculation formula is as follows:

Flag＝min(△y/y0,1)

a＝Flag*aexp＝Flag*k*(△x/max(x0,1))

wherein y0 is a relative transverse distance threshold, k is a proportionality coefficient obtained by a table look-up according to a relative longitudinal distance from a front vehicle and an expected distance, Δ y is a relative transverse distance, x0 is a relative longitudinal distance threshold, and Δ x is a relative longitudinal distance.

The lane where the front target vehicle is located is screened out through the method in the step S2, and then the lane where the front target vehicle is located is switched to the own lane only when the middle point of the tail portion of the front target vehicle of the adjacent lane reaches the lane line of the own lane, and the front target vehicle serving as the functional target vehicle is too late to decelerate or brake strongly in the scene where the front vehicle is cut into the own lane urgently. Therefore, the size of the intention of the cut-in is judged through the calculation of the steps S3 and S4, and if the vehicle delta y in front of the adjacent lane is slightly larger than the distance threshold value y0, the acceleration value of the vehicle is already smaller than the original value; if cut-in continues, the acceleration value of the host vehicle continues to decrease. In this way, the purpose of pre-deceleration is achieved.

And S5, according to the output target vehicle lane change Flag and the set time threshold t0, when the duration time of the target vehicle lane change Flag reaches the set time threshold t0, the system prompts the driver through an instrument or a loudspeaker device.

And S6, based on the outputted target vehicle lane-changing Flag and the information of the deceleration a of the vehicle, the vehicle is driven to follow the vehicle at a safe and comfortable deceleration by the driving/braking system when the front vehicle cuts into the own lane in an emergency.

EXAMPLE III

In the present embodiment, when the cut-in intention determination of the dangerous target vehicle is performed in step S3, the following two methods may be adopted:

1) when the autonomous Vehicle exchanges information in the form of V2X (Vehicle to evolution), the cut-in Vehicle exchanges information with the own Vehicle in the form of V2V or the like, and the lane change information is issued when the autonomous Vehicle cuts in the own lane, so that the own Vehicle can respond to the information in advance, thereby avoiding collision with the cut-in Vehicle or poor comfort of the own Vehicle.

2) Reliable steering lamp information of the front target vehicle is timely provided through the sensing equipment, and the vehicle can respond in advance according to the information, so that collision with the cut-in vehicle is avoided or the comfort of the vehicle is not good.

Example four

As shown in fig. 1, the intelligent detection system for immediate response of emergency cut-in of a preceding vehicle according to an embodiment of the present invention includes the following units:

the lane information acquisition unit is used for acquiring lane line information and front vehicle motion state information through the sensing equipment and judging lane information of the front vehicle;

the dangerous target vehicle detection unit is used for screening a plurality of front vehicles detected by the sensing equipment according to the relative longitudinal distance between the front vehicles and the vehicle according to the lane information of the front vehicles, and preliminarily obtaining a plurality of dangerous target vehicles;

the cut-in intention judging unit is used for calculating the relative transverse/longitudinal distance information, the relative transverse/longitudinal speed and the safe transverse/longitudinal distance between the dangerous target vehicle of the adjacent lane and the vehicle, comprehensively deciding the dangerous target vehicle and judging whether the dangerous target vehicle has a cut-in intention;

the lane marker and deceleration calculating unit is used for calculating the lane change marker of the dangerous target vehicle and the deceleration information of the vehicle according to the motion state of the dangerous target vehicle with the cutting-in intention; the flag bit is used for representing the size of the cut-in intention of the dangerous target vehicle;

the early warning unit is used for setting a time threshold value and sending a prompt to a driver when the duration of the lane change marker bit of the dangerous target vehicle reaches the set time threshold value;

and the active control unit is used for braking the vehicle through the driving/braking system according to the lane change mark bit of the dangerous target vehicle and the deceleration information of the vehicle.

As described above, the present invention determines whether or not there is an intention to change lanes and the magnitude thereof in a preceding vehicle based on information such as lane line information, a preceding vehicle motion state and a host vehicle motion state detected by a sensor device, and a relative longitudinal distance and a lateral distance between the preceding vehicle and the host vehicle, and in a vehicle equipped with an automatic driving function such as constant-speed cruise and adaptive cruise, the intelligent system can adaptively control the vehicle speed in accordance with the magnitude of the intention to change lanes of the preceding vehicle in cooperation with the automatic driving function, thereby ensuring that the relative distance between the preceding vehicle and the host vehicle is within a safe range and ensuring the comfort thereof.

The invention is derived from the fact that when the vehicle is actually driven on the road, the driver can gradually decelerate to ensure safety as the front vehicle cuts into the road, but the front vehicle already cuts into the road and then performs larger deceleration. By introducing the dangerous target vehicle lane change Flag, the deceleration a request of the system is gradually reduced, the effect of operation with an actual driver is achieved, and the comfort of the system is realized on the basis of meeting the safety of the system.

It should be noted that, according to the implementation requirement, each step/component described in the present application can be divided into more steps/components, and two or more steps/components or partial operations of the steps/components can be combined into new steps/components to achieve the purpose of the present invention.

It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.