Vehicle following operation risk state determination method, system and device

Abstract

The embodiment of the present disclosure provides a vehicle car following operation risk state determination method, system and device, which belongs to the technical field of data processing, and specifically comprises the following steps: step 1, obtaining trajectory data of a plurality of artificial driving vehicles in actual road traffic; step 2, dividing all artificial vehicles into K car following groups, each car following group including a front vehicle and a rear vehicle, judging whether the traffic scene of each car following group is normal car following or abnormal car following according to the trajectory data of the rear vehicle of each car following group and a scene discrimination function, and judging whether the driving style of the corresponding driver belongs to aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type based on the trajectory data of the rear vehicle of each normal car following group and a style discrimination function; and step 3, judging the accident risk of each car following group according to the traffic scene and the driving style of the driver of the car following group. Through the scheme of the present disclosure, the determination accuracy and adaptability are improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of data processing, and in particular to a vehicle car-following operation risk state determination method, system and device. BACKGROUND

[0002] At present, with the rapid development of social economy and the continuous advancement of urbanization, the highway network construction is constantly improved, the motorization degree of automobiles is constantly improved, and the demand for road traffic is also improved. At present, the number of motor vehicles and the number of motor vehicle drivers are showing a rapid growth trend, which has brought a series of hidden dangers to the road traffic safety of our country. Among them, rear-end accidents have always been a frequently-occurring type of accident, and the consequences of rear-end collision accidents are also very serious, usually causing a large number of casualties and property losses. Therefore, the research on rear-end accidents has become one of the hotspots in the field of traffic safety. In recent years, satisfactory progress has been made in the research on rear-end accidents, but the research in this field still faces many key problems to be solved, including the consideration of driver heterogeneity in car-following group accident risk determination. Most of the existing car-following group accident risk determination is directly based on alternative safety evaluation indicators, but the differences in car-following scenarios and the reality of driver heterogeneity, so it is necessary to carry out classified and refined research on the accident risk determination of car-following groups.

[0003] Therefore, there is an urgent need for a vehicle car-following operation risk state determination method with higher adaptability and precision. SUMMARY

[0004] Therefore, the embodiments of the present disclosure provide a vehicle car-following operation risk state determination method, system and device, which at least partially solve the problem of poor adaptability and precision in the prior art.

[0005] In a first aspect, the embodiments of the present disclosure provide a vehicle car-following operation risk state determination method, comprising:

[0006] Step 1, obtaining trajectory data of a plurality of artificial driving vehicles in actual road traffic, wherein the trajectory data includes position, speed and acceleration information of each vehicle at each time within a preset time period;

[0007] Step 2, dividing all artificial vehicles into K car-following groups, each car-following group including a front vehicle and a rear vehicle, determining whether the traffic scenario of each car-following group is normal car-following or abnormal car-following according to the trajectory data of the rear vehicle of each car-following group and a scene discrimination function, and determining whether the driving style of the corresponding driver belongs to aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type based on the trajectory data of the rear vehicle of each normal car-following group and a style discrimination function;

[0008] Step 3: Accident risk determination of the car-following group according to the traffic scene and the driving style of the driver of each car-following group.

[0009] According to a specific implementation manner of the embodiment of the present disclosure, the step 1 specifically comprises:

[0010] Collecting a video of actual road traffic, extracting trajectory data of multiple manually driven vehicles from the video by using a video image processing technology, and performing a data cleaning operation on the extracted trajectory data to obtain traffic trajectory data, wherein the data cleaning operation comprises denoising, interpolation and rebalancing.

[0011] According to a specific implementation manner of the embodiment of the present disclosure, the expression of the scene discrimination function is

[0012]

[0013] wherein Δx(t) represents the distance between the rear vehicle and the front vehicle at t = 1, 2…T, v(t) represents the speed of the rear vehicle at t, F3 is the first judgment function value of the traffic scene, and F'3 is the second judgment function value of the traffic scene.

[0014] If F3 < ε1 or F'3 < ε2, it is determined as a non-normal car-following scene, otherwise, it is determined as a normal car-following scene, wherein ε1 and ε2 are preset traffic scene judgment coefficients.

[0015] According to a specific implementation manner of the embodiment of the present disclosure, ε1 = 20 and ε2 = 11.12.

[0016] According to a specific implementation manner of the embodiment of the present disclosure, the expression of the style discrimination function is

[0017]

[0018] wherein v(t) and a(t) respectively represent the speed and acceleration of the rear vehicle at t = 1, 2…T, PRT is the average perception reaction time of the driver of the rear vehicle, T i-1 (n) represents the time of the nth deceleration of the front vehicle, T i (n) represents the time of the nth deceleration of the rear vehicle, N is the total number of decelerations of the car-following group, F4 is the first judgment function value of the driving style, and F'4 is the second judgment function value of the driving style.

[0019] If F4 > β1 and F'4 > β2, it is determined as aggressive non-sensitive type, if F4 < β1 and F'4 > β2, it is determined as conservative non-sensitive type, if F4 > β1 and F'4 < β2, it is determined as aggressive sensitive type, and if F4 < β1 and F'4 < β2, it is determined as conservative sensitive type, wherein β1 and β2 are preset driving style judgment coefficients.

[0020] According to a specific implementation manner of the embodiment of the present disclosure, β1=19.68 and β2=1.24.

[0021] According to a specific implementation manner of the embodiment of the present disclosure, the step 3 specifically comprises:

[0022] If the traffic scene of the current car-following group is normal car-following, steps A1-A2 are executed, otherwise steps A3-A4 are executed.

[0023] In step A1, an initial discriminant function value F1 of the car-following group is calculated according to the following formula:

[0024]

[0025] Wherein, x i-1 (t) and x i (t) are the positions of the front and rear vehicle head centers at time t, v i-1 (t) and v i (t) are the speeds of the front and rear vehicles at time t, and L i-1 is the length of the front vehicle.

[0026] In step A2, if the driving style of the rear driver of the current car-following group is aggressive and non-sensitive, it is determined whether the initial discriminant function value F1 satisfies F1≤μ1. If yes, it is determined that the current car-following group is in a high-risk state, and if not, it is directly determined that the current car-following group is in a non-high-risk state.

[0027] If the driving style of the rear driver of the current car-following group is conservative and non-sensitive, it is determined whether the initial discriminant function value F1 satisfies F1≤μ2. If yes, it is determined that the current car-following group is in a high-risk state, and if not, it is directly determined that the current car-following group is in a non-high-risk state.

[0028] If the driving style of the rear driver of the current car-following group is aggressive and sensitive, it is determined whether the initial discriminant function value F1 satisfies F1≤μ3. If yes, it is determined that the current car-following group is in a high-risk state, and if not, it is directly determined that the current car-following group is in a non-high-risk state.

[0029] If the driving style of the rear driver of the current car-following group is conservative and sensitive, it is determined whether the initial discriminant function value F1 satisfies F1≤μ4. If yes, it is determined that the current car-following group is in a high-risk state, and if not, it is directly determined that the current car-following group is in a non-high-risk state.

[0030] Wherein, μ1, μ2, μ3 and μ4 are the direct discriminant coefficients of the aggressive non-sensitive type, the conservative non-sensitive type, the aggressive sensitive type and the conservative sensitive type driving styles, respectively.

[0031] Step A3, calculate the initial discriminant function value F2 of the required deceleration of the rear vehicle in the car-following group to avoid collision with the corresponding front vehicle at time t:

[0032]

[0033] Where, v i-1 (t) and v i (t) are the vehicle speeds of the front vehicle and the rear vehicle at time t, x i-1 (t) and x i (t) are the vehicle head positions of the front vehicle and the rear vehicle at time t, and L i-1 is the vehicle length of the front vehicle.

[0034] Step A4, determine whether the initial discriminant function value F2 satisfies F2≤θ, if it satisfies, it is determined that the current car-following group is in a non-high risk state, if it does not satisfy, it is directly determined that the current car-following group is in a high risk state, wherein θ refers to the maximum deceleration that the rear vehicle can reach.

[0035] According to a specific implementation manner of the embodiment of the present disclosure, μ1=4, μ2=3, μ3=2, μ4=1; θ=12.68.

[0036] In a second aspect, the embodiment of the present disclosure provides a vehicle car-following operation risk state determination system, comprising:

[0037] An acquisition module is configured to acquire trajectory data of a plurality of artificial driving vehicles in actual road traffic, wherein the trajectory data comprises position, speed and acceleration information of the corresponding vehicle at each time within a preset time period;

[0038] A determination module is configured to divide all artificial vehicles into K car-following groups, each car-following group comprising a front vehicle and a rear vehicle, determine whether the traffic scene of each car-following group is normal car-following or abnormal car-following according to the trajectory data of the rear vehicle of each car-following group and a scene discriminant function, and determine the driving style of the corresponding driver as aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type based on the trajectory data of the rear vehicle of each normal car-following group and a style discriminant function.

[0039] A determination module is configured to determine the accident risk of each car-following group according to the traffic scene and the driving style of the driver of the car-following group.

[0040] In a third aspect, the embodiment of the present disclosure further provides an electronic device, comprising:

[0041] at least one processor; and

[0042] a memory in communication with the at least one processor; wherein

[0043] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the vehicle following operation risk state determination method in the foregoing first aspect or any implementation manner of the first aspect.

[0044] The vehicle following operation risk state determination scheme in the embodiments of the present disclosure includes: step 1, obtaining trajectory data of a plurality of manually driven vehicles in actual road traffic, wherein the trajectory data includes position, speed and acceleration information of each vehicle at each time in a preset time period; step 2, dividing all manually driven vehicles into K following vehicle groups, each following vehicle group including a front vehicle and a rear vehicle, judging the traffic scene of each following vehicle group to be normal following or abnormal following according to the trajectory data of the rear vehicle of each following vehicle group and a scene discrimination function, and discriminating the driving style of the corresponding driver to be aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type based on the trajectory data of the rear vehicle of each normal following vehicle group and a style discrimination function; and step 3, performing accident risk determination on the following vehicle group according to the traffic scene of each following vehicle group and the driving style of the driver.

[0045] The beneficial effects of the embodiments of the present disclosure are as follows: (1) based on high-precision trajectory data of manually driven vehicles in actual road traffic, the traffic scene of the current following vehicle group is discriminated to be normal following or abnormal following; for the normal following vehicle group, the driving style of the rear vehicle driver is discriminated to be aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type. Further, the vehicle following operation state under different traffic scenes and driving styles is analyzed, laying a foundation for classified and refined accident risk assessment of the following vehicle group;

[0046] (2) facing traffic trajectory data, a following vehicle group accident risk assessment model under corresponding traffic scenes and driving styles is constructed, which can accurately calculate the accident risk result under each space-time state, so as to mine the high-risk state of the following vehicle group operation, and help to solve the limitations of directly using alternative safety evaluation indicators in the following vehicle group operation safety evaluation;

[0047] (3) based on a large amount of high-precision trajectory data of manually driven vehicles in a typical traffic area collected by a video, the traffic scene is discriminated and divided according to the distance between the front and rear vehicles and the speed of the rear vehicle during the vehicle following operation; the driving style of the driver is discriminated and divided based on the sum of the absolute values of the speed and acceleration of the rear vehicle and the average perception reaction time of the rear vehicle driver; the method adopted is simple in design, easy to calculate, and directly reflects the differences between different categories of traffic scenes and driving styles;

[0048] (4) The application improves the accuracy of the assessment of the accident risk of the following vehicle group, and clearly determines the method for determining the high-risk state of the following vehicle group operation, which is of great significance to the further development of future traffic safety and has excellent application prospects. BRIEF DESCRIPTION OF DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0050] Figure 1 A flowchart of a vehicle following operation risk state determination method provided by the embodiments of the present disclosure is shown in the figure.

[0051] Figure 2 A technical route diagram of a vehicle following operation risk state determination method provided by the embodiments of the present disclosure is shown in the figure.

[0052] Figure 3 A structural diagram of a vehicle following operation risk state determination system provided by the embodiments of the present disclosure is shown in the figure.

[0053] Figure 4 An electronic device provided by the embodiments of the present disclosure is shown in the figure. DETAILED DESCRIPTION

[0054] The embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0055] The embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0056] It is important to note that the various aspects described herein can be implemented in a wide variety of forms, and that any particular structure and / or function described herein is merely illustrative. An aspect described herein can be implemented independently of any other aspects and / or implemented with any number of the other aspects described herein. For example, an apparatus can implement one but not another aspect described herein. The devices and / or methods described herein can be implemented in any of numerous ways, as will be apparent to one of skill in the art. Furthermore, the described aspects can be implemented alone, or in any combination.

[0057] It is also important to note that the present disclosure can be carried out by more than one process. These processes might or might not be mutually exclusive, and combinations of these processes are possible. That is, a process can have several steps, wherein one step can be carried out by a process that can also carry out another step of the same or different process.

[0058] In addition, in the following description, numerous specific details are provided, such as examples of programming, software modules, user selections, screens, menus, icons, etc. to provide a thorough understanding of examples. One having ordinary skill in the relevant art will recognize, however, that the aspects described herein can be practiced without one or more of the specific details. Also, one will appreciate the drawings are not necessarily drawn to scale and that, where appropriate, dimensional relationships between components in the figures have been exaggerated, removed or minimized, for purposes of simplicity and clarity.

[0059] The embodiments of the present disclosure provide a vehicle car following operation risk state determination method, which can be applied to the analysis of the operation state of a vehicle in a road traffic safety scenario.

[0060] Referring to Figure 1 A flowchart of a vehicle car following operation risk state determination method is provided in the embodiments of the present disclosure. As shown in Figure 1 The method mainly includes the following steps:

[0061] Step 1, obtaining trajectory data of a plurality of artificial driving vehicles in actual road traffic, wherein the trajectory data includes position, speed and acceleration information of the corresponding vehicle at each time in a preset time period;

[0062] Further, the step 1 specifically includes:

[0063] Collecting a video of actual road traffic, extracting trajectory data of a plurality of artificial driving vehicles from the video by using a video image processing technology, and performing a data cleaning operation on the extracted trajectory data to obtain traffic trajectory data, wherein the data cleaning operation includes denoising, interpolation and rebalancing.

[0064] In a specific implementation, as Figure 2As shown, high-precision trajectory data of several manually driven vehicles in actual road traffic can be obtained; wherein the trajectory data includes the position, speed and acceleration information of the corresponding vehicle at each time within a preset time period. The time sequence number of each time in the preset time period is: t = 1, 2, 3, …, T.

[0065] The method for obtaining the trajectory data is: collecting the video of the actual road traffic by aerial photography of the unmanned aerial vehicle, extracting the trajectory data of several manually driven vehicles from the video by using the existing video image processing technology; performing cleaning processes such as denoising, interpolation, and rebalancing on the extracted trajectory data to obtain high-precision micro-traffic trajectory data, and numbering the trajectory data according to the manually driven vehicles.

[0066] Step 2, divide all manually driven vehicles into K car-following groups, each car-following group includes a front vehicle and a rear vehicle, according to the trajectory data of the rear vehicle of each car-following group and the scene discrimination function, judge the traffic scene of the car-following group as normal car-following or abnormal car-following, based on the trajectory data of the rear vehicle of each normal car-following group and the style discrimination function, judge the driving style of the corresponding driver as aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type;

[0067] On the basis of the above embodiment, the expression of the scene discrimination function is

[0068]

[0069] Wherein, Δx(t) represents the distance between the rear vehicle and the front vehicle at t = 1, 2…T, v(t) represents the speed of the rear vehicle at t, F3 is the first judgment function value of the traffic scene, F'3 is the second judgment function value of the traffic scene;

[0070] If F3 < ε1 or F'3 < ε2, it is judged as an abnormal car-following scene, otherwise, it is judged as a normal car-following scene, wherein ε1 and ε2 are preset traffic scene judgment coefficients.

[0071] Optionally, ε1 = 20, ε2 = 11.12.

[0072] Further, the expression of the style discrimination function is

[0073]

[0074] Wherein, v(t) and a(t) represent the speed and acceleration of the rear vehicle at t = 1, 2…T, PRT is the average perception reaction time of the driver of the rear vehicle, T i-1 (n) indicates the time of the nth deceleration of the front vehicle, T i(n) refers to the time of the nth deceleration of the rear vehicle, N is the total number of decelerations of the following vehicle group, F4 is the first judgment function value of the driving style, F'4 is the second judgment function value of the driving style;

[0075] If F4>β1 and F'4>β2, it is judged to be aggressive non-sensitive type, if F4<β1 and F'4>β2, it is judged to be conservative non-sensitive type, if F4>β1 and F'4<β2, it is judged to be aggressive sensitive type, if F4<β1 and F'4<β2, it is judged to be conservative sensitive type, wherein β1 and β2 are preset driving style judgment coefficients.

[0076] Optionally, β1=19.68, β2=1.24.

[0077] In specific implementation, all artificial vehicles can be divided into K following vehicle groups, each following vehicle group includes a front vehicle and a rear vehicle; according to the trajectory data of the rear vehicle of each following vehicle group, it is judged that the traffic scene of the following vehicle group is normal following or abnormal following; based on the trajectory data of the rear vehicle of each normal following vehicle group, it is judged that the driving style of the corresponding driver belongs to aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type.

[0078] The judgment function according to the trajectory data of the rear vehicle of each following vehicle group is that the traffic scene of the following vehicle group is normal following or abnormal following, and the specific judgment function is:

[0079]

[0080] Wherein, Δx(t) represents the distance between the rear vehicle and the front vehicle at t=1, 2…T, v(t) represents the speed of the rear vehicle at t, T is the recording time length of the trajectory data; F3 is the first judgment function value of the traffic scene, F'3 is the second judgment function value of the traffic scene;

[0081] If F3<ε1 or F'3<ε2, it is judged to be an abnormal following scene, otherwise, it is judged to be a normal following scene; wherein ε1 and ε2 are preset traffic scene judgment coefficients.

[0082] The most intuitive feature of whether abnormal following is that the speed of the rear vehicle or the distance between the front vehicle and the rear vehicle in the following vehicle group is too small. Therefore, the judgment conditions mainly include two cases: (1) F3<ε1 is satisfied, but F'3<ε2 is not satisfied, corresponding to the abnormal following under the condition that the distance between the front vehicle and the rear vehicle in the following vehicle group is too small; (2) F'3<ε2 is satisfied, but F3<ε1 is not satisfied, corresponding to the abnormal following under the condition that the speed of the rear vehicle is too small. The judgment condition for the normal following scene is F3>ε1 and F'3>ε2. Therefore, according to the speed of the rear vehicle and the distance between the front vehicle and the rear vehicle in the following vehicle group, the traffic scene of the following vehicle group can be intuitively and accurately simulated and judged as normal following or abnormal following.

[0083] Wherein, ε1 and ε2 are preset traffic scene judgment coefficients, which can be understood as the safe distance and speed corresponding to low-speed driving respectively. Generally, ε1 = 20 can ensure the safe distance in low-speed driving, and ε2 = 11.12 indicates that the vehicle is in low-speed driving state, and the smaller ε1 or ε2 is, the more significant the characteristics of abnormal following is. In the embodiment, ε1 = 20 and ε2 = 11.12 are taken.

[0084] The driving style of the corresponding driver is determined to be aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type according to the trajectory data of the rear vehicle of each normal following vehicle group, and the specific determination function is:

[0085]

[0086] Wherein, v(t) and a(t) represent the speed and acceleration of the rear vehicle at t = 1, 2…T, PRT is the perception reaction time of the rear driver, T i-1 (n) is the time of the nth deceleration of the front vehicle, T i (n) is the time of the nth deceleration of the rear vehicle, N is the total number of decelerations of the following vehicle group; F3 is the first judgment function value of the driving style, F'3 is the second judgment function value of the driving style;

[0087] The most intuitive feature of whether it belongs to aggressive driving style is the speed and its fluctuation (acceleration); the most intuitive feature of whether it belongs to sensitive driving style is that the average perception reaction time of the driver is short, that is, the time difference between the deceleration time of the front vehicle and the corresponding deceleration operation time of the rear vehicle is small. Therefore, the intuitive performance of aggressive non-sensitive driving style is fast driving, large speed fluctuation at adjacent time (that is, large absolute value of acceleration) and long perception reaction time of the driver, so the determination condition is set as F4>β1 and F'4>β2. The intuitive performance of conservative non-sensitive driving style is non-fast driving, small absolute value of acceleration and long perception reaction time of the driver, so the determination condition is set as F4<β1 and F'4>β2. The intuitive performance of aggressive sensitive driving style is fast driving, large absolute value of acceleration and short perception reaction time of the driver, so the determination condition is set as F4>β1 and F'4<β2. And the intuitive performance of conservative sensitive driving style is non-fast driving, not large absolute value of acceleration and short perception reaction time of the driver, so the determination condition is set as F4<β1 and F'4<β2. Therefore, according to the sum of the speed and the absolute value of the acceleration and the average perception reaction time of the driver, the driving style can be more intuitively and accurately determined to be aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type.

[0088] Wherein, β1 and β2 are preset driving style judgment coefficients. β1 can be understood as the sum of the speed threshold value of fast driving and the absolute value of the threshold acceleration corresponding to the comfortable driving feeling. Generally, v = 16.68 means that it is in the fast driving state; and | α | = 3 is the acceleration threshold value of the comfortable driving feeling, and the smaller | α | is, the more comfortable the driving feeling is. Therefore, in the embodiment, β1 = 19.68 is taken. For β2, it can be understood as the average time difference between the time points when the following vehicle group makes multiple deceleration operations corresponding to the front vehicle within the observation period. Generally, the average perception reaction time of the driver is 1.24s, and the smaller β2 is, the higher the driving sensitivity is. Therefore, in the embodiment, β2 = 1.24 is taken.

[0089] Step 3, judging the accident risk of the following vehicle group according to the traffic scene and the driving style of the driver of each following vehicle group.

[0090] On the basis of the above embodiment, the step 3 specifically comprises:

[0091] If the traffic scene of the current following vehicle group is normal following, steps A1-A2 are executed, otherwise steps A3-A4 are executed.

[0092] Step A1, calculating the initial discriminant function value F1 of the running state of the following vehicle group according to the following formula:

[0093]

[0094] Wherein, x i-1 (t) and x i (t) are the head center positions of the front vehicle and the rear vehicle at t moment, v i-1 (t) and v i (t) are the speeds of the front vehicle and the rear vehicle at t moment, and L i-1 is the length of the front vehicle.

[0095] Step A2, if the driving style of the driver of the rear vehicle of the current following vehicle group is aggressive and non-sensitive, judging whether the initial discriminant function value F1 satisfies F1 ≤ μ1, if yes, judging that the current following vehicle group is in a high risk state, if not, directly judging that the current following vehicle group is in a non-high risk state.

[0096] If the driving style of the driver of the rear vehicle of the current following vehicle group is conservative and non-sensitive, judging whether the initial discriminant function value F1 satisfies F1 ≤ μ2, if yes, judging that the current following vehicle group is in a high risk state, if not, directly judging that the current following vehicle group is in a non-high risk state.

[0097] If the driving style of the driver of the rear vehicle of the current car-following group is aggressive and sensitive, it is determined whether the initial discriminant function value F1 satisfies F1≤μ3, if it satisfies, it is determined that the current car-following group is in a high-risk state, if it does not satisfy, it is directly determined that the current car-following group is in a non-high-risk state;

[0098] If the driving style of the driver of the rear vehicle of the current car-following group is conservative and sensitive, it is determined whether the initial discriminant function value F1 satisfies F1≤μ4, if it satisfies, it is determined that the current car-following group is in a high-risk state, if it does not satisfy, it is directly determined that the current car-following group is in a non-high-risk state;

[0099] Wherein, μ1, μ2, μ3 and μ4 are direct discriminant coefficients of aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type and conservative sensitive type driving style respectively;

[0100] Step A3, the initial discriminant function value F2 of the required deceleration of the rear vehicle of the car-following group to avoid collision with the corresponding front vehicle at t time is calculated:

[0101]

[0102] Wherein, v i-1 (t) and v i (t) are the vehicle speeds of the front vehicle and the rear vehicle at t time, x i-1 (t) and x i (t) are the vehicle head center positions of the front vehicle and the rear vehicle at t time, and L i-1 is the vehicle length of the front vehicle.

[0103] Step A4, it is determined whether the initial discriminant function value F2 satisfies F2≤θ, if it satisfies, it is determined that the current car-following group is in a non-high-risk state, if it does not satisfy, it is directly determined that the current car-following group is in a high-risk state, wherein, θ refers to the maximum deceleration that the rear vehicle can reach.

[0104] Optionally, μ1=4, μ2=3, μ3=2, μ4=1; θ=12.68.

[0105] In specific implementation, the steps of determining the accident risk of the car-following group under different traffic scenes and driving styles can be as follows:

[0106] Step A1, for the car-following group under the non-normal car-following traffic scene determined in step 2, the initial discriminant function value F2 of the required deceleration of the rear vehicle to avoid collision with the corresponding front vehicle of the car-following group at t time is calculated:

[0107]

[0108] Wherein, v i-1 (t) and v i(t) and x i-1 (t) and x i (t) and x i-1 is the length of the front vehicle.

[0109] If the initial discriminant function value F2 satisfies F2≤θ, it is determined that the current car-following group is in a non-high-risk state, otherwise it is directly determined that the current car-following group is in a high-risk state; wherein θ refers to the maximum deceleration that the rear vehicle can reach. In this embodiment, θ=12.68 is taken.

[0110] Step A2, for the car-following group in the normal car-following traffic scene determined in step 2, the initial discriminant function value F1 of the car-following group running state is calculated according to the following formula:

[0111]

[0112] wherein x i-1 (t) and x i (t) are the head center positions of the front and rear vehicles at t, v i-1 (t) and v i (t) are the speeds of the front and rear vehicles at t, and L i-1 is the length of the front vehicle.

[0113] If the driving style of the rear driver of the current car-following group is determined to be aggressive and non-sensitive in step 2, it is determined whether the initial discriminant function value F1 satisfies F1≤μ1, if it satisfies, it is determined that the current car-following group is in a high-risk state, if it does not satisfy, it is directly determined that the current car-following group is in a non-high-risk state.

[0114] If the driving style of the rear driver of the current car-following group is determined to be conservative and non-sensitive in step 2, it is determined whether the initial discriminant function value F1 satisfies F1≤μ2, if it satisfies, it is determined that the current car-following group is in a high-risk state, if it does not satisfy, it is directly determined that the current car-following group is in a non-high-risk state.

[0115] If the driving style of the rear driver of the current car-following group is determined to be aggressive and sensitive in step 2, it is determined whether the initial discriminant function value F1 satisfies F1≤μ3, if it satisfies, it is determined that the current car-following group is in a high-risk state, if it does not satisfy, it is directly determined that the current car-following group is in a non-high-risk state.

[0116] If the driving style of the driver of the rear vehicle in the current car-following group is conservative and sensitive in step 2, it is determined whether the initial discriminant function value F1 satisfies F1≤μ4.If it satisfies, it is determined that the current car-following group is in a high-risk state.If it does not satisfy, it is directly determined that the current car-following group is in a non-high-risk state.

[0117] Wherein, μ1, μ2, μ3 and μ4 are respectively the direct discriminant coefficients of the driving styles of aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type and conservative sensitive type; in this embodiment, μ1=4, μ2=3, μ3=2 and μ4=1.

[0118] The vehicle car-following running risk state determination method provided in this embodiment determines whether the traffic scene of the current car-following group is normal car-following or abnormal car-following based on the high-precision trajectory data of the manually driven vehicles in the actual road traffic; for the normal car-following group, the driving style of the driver of the rear vehicle is determined to belong to aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type. Further, the car-following running state under different traffic scenes and driving styles is analyzed, which lays a foundation for the classification and refined accident risk assessment of the car-following group.

[0119] For the traffic trajectory data, the car-following group accident risk assessment model under the corresponding traffic scene and driving style conditions is constructed, which can accurately calculate the accident risk result under each space-time state, so as to mine the high-risk state of the car-following group running, which helps to solve the limitations of directly using the alternative safety assessment indicators in the car-following group running safety assessment;

[0120] Based on the high-precision trajectory data of a large number of manually driven vehicles in a typical traffic area collected by video, the traffic scene is distinguished and divided according to the distance between the front and rear vehicles and the speed of the rear vehicle during the car-following running process; the driving style of the driver is distinguished and divided based on the sum of the absolute values of the speed and acceleration of the rear vehicle and the average perception reaction time of the driver of the rear vehicle; the method used is simple in design, easy to calculate, and directly reflects the differences between different categories of traffic scenes and driving styles, improves the accuracy of the car-following group accident risk assessment, and clearly determines the method for determining the high-risk state of the car-following group running, which is of great significance to the further development of future traffic safety and has excellent application prospects.

[0121] The present scheme will be described below in conjunction with a specific embodiment, S1: high-precision manually driven vehicle trajectory data is obtained by collecting road traffic videos by unmanned aerial vehicle aerial photography, and vehicle trajectory data processing is performed by video image processing and data cleaning technology. The trajectory data contains vehicle position, speed and acceleration information every second, and the vehicle is labeled (i.e. vehicle ID).

[0122] The following is the first car group, k is the group number, k = 1, 2, …, K, K = 10. The total duration of data record is divided into T time, t is the time sequence number, t = 1, 2, …, T, T = 5.

[0123] The trajectory data of the first car group and its rear car 2 are shown in Table 1:

[0124]

[0125] Table 1

[0126] The trajectory data of the second car group and its rear car 9 are shown in Table 2:

[0127]

[0128] Table 2

[0129] S2: The large amount of high-precision trajectory data of artificial driving vehicles obtained in step S1 is classified into two types of traffic scenes, i.e. typical normal following and abnormal following.

[0130] The average distance between the front and rear cars of the first car group within 1-5s is calculated by using the discriminant function F3:

[0131]

[0132] The average speed of the rear car of the first car group within 1-5s is calculated by using the discriminant function F'3:

[0133]

[0134] It can be seen that 10.62 < 20, i.e. F3 < ε1, so it is determined that the first car group is in an abnormal following scene.

[0135] The average distance between the front and rear cars of the second car group within 1-5s is calculated by using the discriminant function F3:

[0136]

[0137] The average speed of the rear car of the second car group within 1-5s is calculated by using the discriminant function F'4:

[0138]

[0139] It can be seen that 21.09 > 20, i.e. F3 > ε1, and 27.74 > 11.12, i.e. F'3 > ε2, so it is determined that the second car group is in a normal following scene.

[0140] S3: The trajectory data of the artificial driving vehicle in the normal car-following scenario obtained in step S2 is subjected to four types of driving style discrimination and division of the rear driver, i.e., aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type and conservative sensitive type.

[0141] The average value of the sum of the speed and the absolute value of the acceleration of the rear vehicle in the second car-following group within 1-5s is calculated by using the discrimination function F4:

[0142]

[0143] The average perception reaction time of the rear driver of the second car-following group within 1-5s is calculated by using the discrimination function F'4:

[0144]

[0145] It can be seen that 28.1>19.68, i.e., F4>β1, and 1<1.24, i.e., F'4<β2, so it is determined that the driving style of the rear driver of the second car-following group belongs to the aggressive sensitive type.

[0146] S4: Based on the car-following groups obtained in step S2, the accident risk is determined. The specific steps are as follows:

[0147] S4.1 The initial discrimination function value F2 of the required deceleration of the rear vehicle 2 to avoid collision with the corresponding car-following group front vehicle 1 at t=1, 2, 3, 4, 5s is calculated for the first group of non-normal car-following groups:

[0148]

[0149] It can be seen that 11.42, 6.17 and 3.63 are all less than 12.68, while 13.19 and 16.78 are all greater than 12.68, i.e., F2<θ when t=2, 3, 4s, and F2>θ when t=1, 5s. Therefore, it is determined that the first group of car-following groups is in a low risk state at t=2, 3, 4s, and in a high risk state at t=1, 5s.

[0150] S4.2 The initial discrimination function value F1 of the running state of the car-following group at t=1, 2, 3, 4, 5s is calculated for the second group of normal car-following groups:

[0151]

[0152] It can be seen that 10.5, 12.83, 6.62, 7.45 and 8.19 are all greater than 2, i.e., F1≥μ3 when t=1, 2, 3, 4, 5s, so it is determined that the second group of car-following groups is in a low risk state at t=1, 2, 3, 4, 5s.

[0153] Corresponding to the method embodiments above, refer to Figure 3 The embodiment of the present disclosure also provides a vehicle car-following operation risk state determination system 30, comprising:

[0154] An acquisition module 301 is configured to acquire trajectory data of a plurality of artificial driving vehicles in actual road traffic, wherein the trajectory data comprises position, speed and acceleration information of each vehicle at each time point within a preset time period;

[0155] A determination module 302 is configured to divide all artificial vehicles into K car-following groups, each car-following group comprising a front vehicle and a rear vehicle, determine, according to trajectory data of the rear vehicle of each car-following group and a scene determination function, a traffic scene of the car-following group as normal car-following or abnormal car-following, and determine, based on trajectory data of the rear vehicle of each normal car-following group and a style determination function, a driving style of a corresponding driver as aggressive non-sensitive, conservative non-sensitive, aggressive sensitive or conservative sensitive.

[0156] A determination module 303 is configured to determine, according to the traffic scene of each car-following group and the driving style of the driver, an accident risk of the car-following group.

[0157] Figure 3 The system shown can correspondingly execute the content in the above method embodiments, and parts not described in detail in the present embodiment are referred to the content described in the above method embodiments, which will not be described here again.

[0158] Corresponding to the method embodiments above, refer to Figure 4 The embodiment of the present disclosure also provides an electronic device 40, comprising at least one processor and a memory connected with the at least one processor. Wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the vehicle car-following operation risk state determination method in the above method embodiments.

[0159] The embodiment of the present disclosure also provides a non-transitory computer readable storage medium, which stores computer instructions for causing the computer to execute the vehicle car-following operation risk state determination method in the above method embodiments.

[0160] The embodiment of the present disclosure also provides a computer program product, which comprises a computer program stored on a non-transitory computer readable storage medium, and the computer program comprises program instructions, when the program instructions are executed by a computer, causing the computer to execute the vehicle car-following operation risk state determination method in the above method embodiments.

[0161] The following refers to Figure 4FIG. 1 shows a block diagram of an electronic device 40 suitable for use in implementing embodiments of the present disclosure. The electronic device in embodiments of the present disclosure can include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet PC), a PMP (Portable Multimedia Player), a car terminal (e.g., a car navigation terminal), and the like, as well as a stationary terminal such as a digital TV, a desktop computer, and the like. Figure 4 The electronic device shown is merely one example and should not be taken as limiting the functionality or use of embodiments of the present disclosure.

[0162] As shown in FIG. 1, the electronic device 40 can include a processing device (e.g., a central processor, a graphic processor, etc.) 401 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 402 or loaded into a random access memory (RAM) 403 from a storage device 408. Various programs and data required for the operation of the electronic device 40 are also stored in the RAM 403. The processing device 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404. Figure 4

[0163] Generally, the following devices can be connected to the I / O interface 405: input devices 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, and the like; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; storage devices 408 including, for example, a magnetic tape, a hard disk, and the like; and communication devices 409. The communication devices 409 can allow the electronic device 40 to communicate wirelessly or wiredly with other devices to exchange data. Although the electronic device 40 having various devices is shown in the drawing, it should be understood that all of the shown devices are not required to be implemented or possessed. More or less devices can be alternatively implemented or possessed.

[0164] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product including a computer program carried on a computer readable medium, the computer program containing program codes for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication devices 409, or installed from the storage devices 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-described functions defined in the methods of the present disclosure are performed.

[0165] ​It should be noted that the computer readable medium in the above disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. The computer readable storage medium may, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, a RF (radio frequency) or the like, or any suitable combination of the above.

[0166] The computer readable medium described above can be contained in the electronic device described above; or can exist separately and not be assembled into the electronic device.

[0167] The computer readable medium described above carries one or more programs, which, when executed by the electronic device, enable the electronic device to perform the related steps of the method embodiments described above.

[0168] Alternatively, the computer readable medium described above carries one or more programs, which, when executed by the electronic device, enable the electronic device to perform the related steps of the method embodiments described above.

[0169] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0170] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0171] The units described in the embodiments of the present disclosure can be implemented by software, or by hardware, or by a combination of software and hardware.

[0172] It should be understood that each part of the present disclosure can be implemented by hardware, software, firmware, or a combination thereof.

[0173] The above description is merely illustrative of the disclosure and not limiting thereof; and any changes or modifications that can be readily deduced within the technical scope of the present disclosure should be encompassed within the scope of the present disclosure. Therefore, the scope of the present disclosure should be based on the scope of the claims.

Claims

1. A vehicle car following operation risk state determination method characterized by, The method comprises the following steps: Step 1, obtaining trajectory data of a plurality of manually driven vehicles in actual road traffic, wherein the trajectory data comprises position, speed and acceleration information of the corresponding vehicle at each time within a preset time period; Step 2, divide all artificial vehicles into a plurality of car-following groups, each car-following group including a front vehicle and a rear vehicle, determine, according to trajectory data of the rear vehicle of each car-following group and a scene discrimination function, whether a traffic scene of the car-following group is normal car-following or abnormal car-following, and determine, based on trajectory data of the rear vehicle of each normal car-following group and a style discrimination function, whether a driving style of a corresponding driver belongs to aggressive non-sensitive type, conservative non-sensitive type, aggressive sensitive type or conservative sensitive type, wherein an expression of the style discrimination function is ； in, and They respectively indicate that the following vehicle is in Velocity and acceleration at any moment The average perception reaction time of the driver of the following vehicle. The car in front The moment of deceleration. The rear carriage The moment of deceleration. The total number of decelerations for the following train group. The first function value for determining driving style. This is the value of the second judgment function for driving style; If and , it is determined to be the radical non-sensitive type, if and , it is determined to be the conservative non-sensitive type, if and , it is determined to be the radical sensitive type, if and , it is determined to be the conservative sensitive type, wherein, and are preset driving style judgment coefficients. Step 3, judging the accident risk of each car-following group according to the traffic scene and the driving style of the driver of the car-following group.

2. The method of claim 1, wherein The step 1 specifically comprises: Collecting a video of actual road traffic, extracting trajectory data of a plurality of manually driven vehicles from the video by using a video image processing technology, and performing data cleaning operation on the extracted trajectory data to obtain traffic trajectory data, wherein the data cleaning operation comprises noise removal, interpolation and rebalancing.

3. The method of claim 1, wherein The expression of the scene discrimination function is ； wherein, denotes the distance between the rear vehicle and the front vehicle at time denotes the speed of the rear vehicle at time is the first judgment function value of the traffic scenario, is the second judgment function value of the traffic scenario;​​ If or , it is determined as an abnormal car-following scene, otherwise, it is determined as a normal car-following scene, wherein, and are preset traffic scene judgment coefficients.

4. The method of claim 3, wherein , ， 。 5. The method of claim 1, wherein , ， 。 6. The method of claim 1, wherein The step 3 specifically comprises: If the traffic scene of the current car-following group is normal following, steps A1-A2 are executed, otherwise steps A3-A4 are executed. Step A1, the initial discriminant function value of the operation state of the car group is calculated according to the following formula : ； wherein, and are respectively the positions of the centers of the front and rear vehicle's vehicle head at the moment, and are respectively the speeds of the front and rear vehicle at the moment, the length of the front vehicle; Step A2, if the driving style of the driver of the following vehicle of the current car-following group is aggressive and insensitive, determine whether the initial discriminant function value satisfies If yes, determine that the current car-following group is in a high-risk state, and if no, directly determine that the current car-following group is in a non-high-risk state. If the driving style of the driver of the rear vehicle of the current car-following group is conservative and non-sensitive, it is judged whether the initial discrimination function value satisfies If it satisfies, it is judged that the current car-following group is in a high-risk state, and if it does not satisfy, it is directly judged that the current car-following group is in a non-high-risk state. If the driving style of the driver of the rear vehicle of the current car-following group is aggressive and sensitive, it is judged whether the initial discrimination function value satisfies If it satisfies, it is judged that the current car-following group is in a high-risk state, and if it does not satisfy, it is directly judged that the current car-following group is in a non-high-risk state. If the driving style of the driver of the rear vehicle of the current car-following group is conservative and sensitive, it is judged whether the initial discrimination function value satisfies If it satisfies, it is judged that the current car-following group is in a high-risk state, and if it does not satisfy, it is directly judged that the current car-following group is in a non-high-risk state. wherein, , , and are the direct discriminant coefficients for aggressive non-sensitive, conservative non-sensitive, aggressive sensitive and conservative sensitive driving styles, respectively. Step A3, calculate the initial discriminant function value of the required deceleration for avoiding collision with the corresponding front vehicle at the time of the rear vehicle in the car-following group Step A4, determine the required deceleration for avoiding collision with the corresponding front vehicle at the time of the rear vehicle in the car-following group Step A5, determine the required deceleration for avoiding collision with the corresponding front vehicle at the time of the ； wherein, and are the vehicle speeds of the front and rear vehicles at time and are the vehicle headway positions of the front and rear vehicles at time is the vehicle length of the front vehicle;​​ Step A4, judging whether the initial discriminant function value satisfies If yes, it is judged that the current car-following group is in a non-high risk state, and if not, it is directly judged that the current car-following group is in a high risk state, wherein, is the maximum deceleration that the following vehicle can reach.​ 7. The method of claim 6, wherein , 4， ， 2， ； 。 8. A car-following operation risk state determination system characterized by comprising: The method comprises the following steps: An acquisition module is configured to acquire trajectory data of a plurality of manually driven vehicles in actual road traffic, wherein the trajectory data comprises position, speed and acceleration information of the corresponding vehicle at each time within a preset time period; The discrimination module is used to classify all manual vehicles into... Each car-following vehicle group includes a leading vehicle and a trailing vehicle. Based on the trajectory data of the trailing vehicle in each car-following vehicle group and a scene discrimination function, the traffic scene of that car-following vehicle group is determined to be either normal car-following or abnormal car-following. Based on the trajectory data of the trailing vehicle in each normal car-following vehicle group and a style discrimination function, the driving style of the corresponding driver is determined to be either aggressive and insensitive, conservative and insensitive, aggressive and sensitive, or conservative and sensitive. The expression for the style discrimination function is as follows: ； in, and They respectively indicate that the following vehicle is in Velocity and acceleration at any moment The average perception reaction time of the driver of the following vehicle. The car in front The moment of deceleration. The rear carriage The moment of deceleration. The total number of decelerations for the following train group. The first function value for determining driving style. This is the value of the second judgment function for driving style; If and , it is determined as radical non-sensitive type, if and , it is determined as conservative non-sensitive type, if and , it is determined as radical sensitive type, if and , it is determined as conservative sensitive type, wherein, and are preset driving style judgment coefficients. A judgment module is configured to judge the accident risk of each car-following group according to the traffic scene and the driving style of the driver of the car-following group.

9. An electronic device, comprising: The electronic device comprises: At least one processor; and A memory connected in communication with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the vehicle car-following operation risk state judgment method in any one of the preceding claims 1-7.

Images