A Cooperative Method for High-Risk Scenario Identification and Passive Safety Based on Critical Risk-Avoidance State

Abstract

The present application discloses a method for high-risk scenario recognition and passive safety collaboration based on a critical risk avoidance state, including: obtaining current target vehicle state data; determining the critical risk avoidance time based on the current target vehicle state data T cep ; calculating the successfully avoidable time according to the current target vehicle state data and the critical risk avoidance time T cep ; using the successfully avoidable time for high-risk scenario recognition. When no high-risk scenario is recognized, the current vehicle distance is re-obtained. When a high-risk scenario is recognized, passive safety constraints are carried out in stages using a passive safety collaboration strategy; the present application uses the critical risk avoidance time to characterize the spatio-temporal proximity of the vehicle, improves the high-risk scenario recognition ability of the target vehicle, can initiate a timely passive safety collaboration response in high-risk scenarios, improves the safety factor of the target vehicle, and reduces the incidence of traffic accidents.

Description

Technical Field

[0001] The present application relates to the technical field of autonomous driving, and particularly to a method for identifying high-risk scenarios and passive safety collaboration based on a critical risk avoidance state. Background Art

[0002] The technology of autonomous vehicles can reduce human errors to a certain extent, thereby reducing the incidence of traffic accidents and minimizing personal injuries, and thus has received increasing attention. At present, the safety performance of autonomous vehicles is still being continuously improved and enhanced. Among them, accurately characterizing risks is the basis and key for improving the safety performance of autonomous vehicles. Previous studies have evaluated the driving risks of vehicles from different perspectives and formulated vehicle braking control strategies based on these evaluations. In some cases, the underlying risk expression indicators mainly include: safety distance indicators, time-to-collision indicators, and subjective cognitive judgment indicators of drivers, etc. The applicable scenarios of autonomous driving are also constantly evolving and developing. For example, the evaluation scenarios have gradually evolved from single longitudinal safety control evaluations such as CCRs (Car-to-Car Rear Stationary) and CCRm (Car-to-Car Relative Motion) to vehicle steering scenarios. Previous decision control algorithms using TTC (Time to collision) as a risk indicator are only sensitive to objects in the current driving direction, and lack corresponding risk estimation methods for scenarios where the target vehicle steers (the target object is not on the extension line of the current driving direction of the target vehicle). It is necessary to find risk assessment methods applicable to steering scenarios and conduct test analyses.

[0003] In some cases, the autonomous driving method still has deficiencies in expressing risks. The factors considered in its risk assessment method are not comprehensive enough, the identification of high-risk scenarios is not accurate enough. In addition, the autonomous driving technology fails to demonstrate the passive safety response ability of the vehicle in the current environment. Summary of the Invention

[0004] The purpose of the present application is to provide a method for identifying high-risk scenarios and passive safety collaboration based on a critical risk avoidance state, which can improve the identification ability of the target vehicle for high-risk scenarios, enable timely passive safety collaboration responses to be initiated in high-risk scenarios, improve the safety factor of the target vehicle, and reduce the incidence of traffic accidents.

[0005] To achieve the above purpose, the present application provides the following solutions.

[0006] The present application provides a method for identifying high-risk scenarios and passive safety collaboration based on a critical avoidance state. The method for identifying high-risk scenarios and passive safety collaboration based on a critical avoidance state includes: obtaining current target vehicle state data; the current target vehicle state data at least includes: the current driving state of the target vehicle, the current vehicle distance, the current speed of the target vehicle, and the current acceleration of the target vehicle; the current driving state of the target vehicle is straight or turning; the current vehicle distance is the distance between the target vehicle and the vehicle to be avoided; determining the critical avoidance time based on the current target vehicle state data Tcep ; the critical avoidance time Tcep is the time from the critical avoidance point to the time when the target vehicle and the vehicle to be avoided are about to collide; the critical avoidance point is the shortest distance required for the target vehicle to successfully avoid the vehicle to be avoided; calculating the successfully avoidable time according to the current target vehicle state data and the critical avoidance time Tcep ; using the successfully avoidable time to identify high-risk scenarios. When no high-risk scenario is identified, the current vehicle distance is re-obtained. When a high-risk scenario is identified, passive safety constraints are carried out in stages using a passive safety collaboration strategy; the high-risk scenario is a scenario where the successfully avoidable time is less than or equal to a preset time; the passive safety constraints include: seat belt constraint and / or airbag constraint.

[0007] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application.

[0008] The present application determines the critical avoidance time through the current target vehicle state data Tcep , and calculates the successfully avoidable time according to the current target vehicle state data and the critical avoidance time Tcep ; uses the successfully avoidable time to identify high-risk scenarios, and characterizes the spatio-temporal proximity of the vehicle by the critical avoidance time, improving the ability of the target vehicle to identify high-risk scenarios; when a high-risk scenario is identified, passive safety constraints are carried out in stages using a passive safety collaboration strategy, which can initiate timely passive safety collaboration responses in high-risk scenarios, improve the safety factor of the target vehicle, and reduce the incidence of traffic accidents. Description of the Drawings

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0010] Figure 1 is a flowchart of a method for identifying high-risk scenarios and passive safety collaboration based on a critical avoidance state provided by an embodiment of the present application Figure 1 .

[0011] Figure 2 Schematic diagram of the process of a method for high-risk scenario recognition and passive safety coordination based on critical risk avoidance state provided by an embodiment of the present application Figure 2 。

[0012] Figure 3 Schematic diagram of the positional relationship of the risk avoidance critical point provided by an embodiment of the present application.

[0013] Figure 4 Schematic diagram of the vehicle position relationship when the target vehicle is going straight provided by an embodiment of the present application.

[0014] Figure 5 Schematic diagram of the vehicle position relationship when the target vehicle is turning provided by an embodiment of the present application.

[0015] Figure 6 Schematic diagram of the time for successful risk avoidance provided by an embodiment of the present application.

[0016] Figure 7 Simulation scenario diagram provided by an embodiment of the present application.

[0017] Figure 8 Graph of straight-ahead vertical collision speed and braking force provided by an embodiment of the present application.

[0018] Figure 9 Graph of straight-ahead rear-end collision speed and braking force provided by an embodiment of the present application.

[0019] Figure 10 Graph of straight-ahead oncoming collision speed and braking force provided by an embodiment of the present application.

[0020] Figure 11 Graph of turning collision speed and braking force provided by an embodiment of the present application. Detailed implementation manners

[0021] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0022] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0023] Embodiment 1, as Figure 1 - Figure 2As shown in the figure, this embodiment provides a method for identifying high-risk scenarios and coordinating passive safety based on the critical avoidance state. The method includes the following steps.

[0024] S1. Obtain the current target vehicle status data; the current target vehicle status data at least includes: the current target vehicle driving status, the current vehicle distance, the current target vehicle speed, and the current target vehicle acceleration; the current target vehicle driving status is straight or turning; the current vehicle distance is: the distance between the target vehicle and the vehicle to be avoided.

[0025] Optionally, the vehicle to be avoided is a two-wheeler or a car.

[0026] S2. As Figure 3 - Figure 5 shown, determine the critical avoidance time based on the current target vehicle status data T cep ; the critical avoidance time T cep is the time from the critical avoidance point to the time when the target vehicle and the vehicle to be avoided are about to collide; the critical avoidance point is the shortest distance required for the target vehicle to successfully avoid the vehicle to be avoided.

[0027] Optionally, the Collision Evasion Point (CEP) is when the current vehicle distance is lower than a specific value and the target vehicle has not taken evasive actions. Although the driver may adopt various evasive actions such as deceleration and steering, the collision is inevitable. This specific value is the critical avoidance point.

[0028] Step S2 specifically includes the following steps.

[0029] S21. As Figure 4 shown, when the current target vehicle driving status is straight, calculate the avoidance time for each straight-ahead avoidance scenario using the avoidance conditions in different straight-ahead avoidance scenarios, and select the shortest time among the avoidance times for each straight-ahead avoidance scenario as the critical avoidance time T cep ; the straight-ahead avoidance scenarios at least include: the first scenario, the second scenario, and the third scenario; the first scenario is the scenario where the target vehicle decelerates to avoid the vehicle to be avoided; the second scenario is the scenario where the target vehicle turns in the same direction to avoid the vehicle to be avoided; the third scenario is the scenario where the target vehicle turns in the opposite direction to avoid the vehicle to be avoided.

[0030] Furthermore, calculating the avoidance time for each straight-ahead avoidance scenario using the avoidance conditions in different straight-ahead avoidance scenarios specifically includes the following steps.

[0031] 1) Establish the 1-axis in the direction of the target vehicle's motion x and the direction perpendicular to the x 1-axis as the x2 axes, a first coordinate system with the current position of the target vehicle as the coordinate origin.

[0032] 2) Using the risk avoidance conditions in the first scenario with the minimum current vehicle distance as the goal, determine the risk avoidance distance in the first scenario, and calculate the risk avoidance time in the first scenario based on the risk avoidance distance in the first scenario; where the risk avoidance conditions in the first scenario are as follows.

[0033] v 1 2 ≤ v 2 2 ·cos 2 θ +2· a 1· μ · g · m .

[0034] In the formula, v 1 is the speed of the target vehicle, v 2 is the speed of the vehicle to be avoided, θ is the angle between the speed direction of the vehicle to be avoided and the x 1 axis of the first coordinate system, a 1 is the maximum acceleration of the target vehicle along the x 1 axis, μ is the ground friction coefficient, g is the gravitational acceleration, m is the current vehicle distance.

[0035] 3) Using the risk avoidance conditions in the second scenario with the minimum current vehicle distance as the goal, determine the risk avoidance distance in the second scenario, and calculate the risk avoidance time in the second scenario based on the risk avoidance distance in the second scenario; where the risk avoidance conditions in the second scenario are as follows.

[0036] v 1 2 ≤ v 2 2 ·cos 2 θ +2· a 1· μ · g · m .

[0037] Lx 1 - d1 / 2 - ( d 2·sinθ) / 2 + a ≥ Lx 2.

[0038] In the formula, d 1 is the width of the target vehicle, d 2 is the length of the vehicle to be avoided, Lx1 is the lateral displacement of the vehicle, Lx 2 is the lateral displacement of the vehicle to be avoided, a which is the perpendicular distance between the vehicle to be avoided and the x 1-axis of the first coordinate system.

[0039] Optionally, the calculation formula for the lateral displacement of the vehicle is as follows.

[0040] Lx 1 =(t 2 ·a 2 ) / 2.

[0041] Optionally, the calculation formula for the lateral displacement of the vehicle to be avoided is as follows.

[0042] Lx 2 =v 2 ·t· sin θ .

[0043] 4) Using the risk avoidance conditions in the third scenario with the minimum current vehicle distance as the goal, determine the risk avoidance distance in the third scenario, and calculate the risk avoidance time in the third scenario based on the risk avoidance distance in the third scenario; where the risk avoidance conditions in the third scenario are as follows.

[0044] v 1 2 ≤ v 2 2 ·cos 2 θ +2· a 1· μ · g · m .

[0045] Lx 1 +Lx 2 ≤a - d 1 / 2-(d 2 ·sinθ) / 2 .

[0046] S22. As Figure 5 shown, when the current target vehicle's driving state is turning, calculate the risk avoidance time in each turning risk avoidance scenario using the risk avoidance conditions in different turning risk avoidance scenarios, and select the shortest time among the risk avoidance times in each turning risk avoidance scenario as the critical risk avoidance time T cep; The steering risk avoidance scenarios at least include: the fourth scenario, the fifth scenario, and the sixth scenario; the fourth scenario is a scenario where the target vehicle's speed in the driving direction of the vehicle to be avoided has been reduced to 0 before the target vehicle reaches the driving route of the vehicle to be avoided; the fifth scenario is a scenario where the target vehicle passes through the driving route of the vehicle to be avoided from behind the vehicle to be avoided and then keeps driving behind the vehicle to be avoided; the sixth scenario is a scenario where the target vehicle passes through the driving route of the vehicle to be avoided in front of the vehicle to be avoided and then keeps driving in front of the vehicle to be avoided.

[0047] Furthermore, the risk avoidance time for each steering risk avoidance scenario is calculated using the risk avoidance conditions under different steering risk avoidance scenarios, which specifically includes the following steps.

[0048] 1) Establish a second coordinate system with the moving direction of the vehicle to be avoided as x axis 1, with the direction perpendicular to x axis 1 as x axis 2, and the current position of the vehicle to be avoided as the coordinate origin.

[0049] Optionally, the current vehicle distance is m , project the target vehicle's coverage space onto x axis 1 in the second coordinate system. Calculate the distance x 0 from the center point of the vehicle to be avoided to the center point of the target vehicle's projection, the distance y 0 from the center point of the target vehicle to the center point of the target vehicle's projection, and the angle γ between the speed direction of the vehicle to be avoided and the speed direction of the target vehicle.

[0050] 2) Using the risk avoidance condition in the fourth scenario with the minimum current vehicle distance as the goal, determine the risk avoidance distance in the fourth scenario, and calculate the risk avoidance time in the fourth scenario based on the risk avoidance distance in the fourth scenario; among them, the risk avoidance condition in the fourth scenario is as follows.

[0051] v y (t)=0 .

[0052] y(t) ≤ y 0.

[0053] Among them, v y (t) is the speed of the target vehicle in the t axis 1 direction in the second coordinate system at time x , y(t) is the displacement passed by the target vehicle in the t axis 1 direction in the second coordinate system at time x , y 0 is the distance between the target vehicle and the vehicle to be avoided in the second coordinate system at xInitial spacing in the 1-axis direction.

[0054] Optionally, first calculate the splitting of the acceleration of the target vehicle and decompose the acceleration of the target vehicle onto x 1, x to obtain on the 2-axis a x ( t ) with a y ( t). a x (t) The calculation formula is as follows.

[0055] a x ( t ) =a x1 (t) + a x2 (t) .

[0056] Among them, a x1 (t) is the maximum longitudinal acceleration of the target vehicle a 1 in x the component of 1, a x2 (t) is the maximum lateral acceleration (deceleration) of the target vehicle a 2 in x the component of 1. a x1 (t) The calculation formula is as follows.

[0057] a x1 ( t ) =a 1 · cos γ ( t ).

[0058] Among them, γ ( t ) is t the angle between the velocity direction of the vehicle to be avoided and the velocity direction of the target vehicle at time, and its initial value is γ . a x2 (t) The calculation formula is as follows.

[0059] a x2 (t) = a 2 · sin γ(t) .

[0060] a y (t) The calculation formula is as follows.

[0061] a y (t) = a y1 (t) + a y2 (t) .

[0062] Among them, a y1 (t) is the maximum longitudinal acceleration (deceleration) of the target vehicle a 1 in x the component of 2, a y2 (t) is the maximum lateral acceleration (deceleration) of the target vehicle a 2 in x the component of 2. a y1 (t) The calculation formula is as follows.

[0063] a y1 (t) = a 1 ·sinγ(t) .

[0064] a y2 (t) The calculation formula is as follows.

[0065] a y2 (t) = a 2 ·cosγ(t) .

[0066] Calculation interval time Δt After that, the calculation formula for the angle between the speed direction of the vehicle to be avoided and the target vehicle speed is as follows.

[0067] γ(t + Δt) = γ(t) - ω(t)·Δt .

[0068] Among them, ω(t) The calculation formula for the angular velocity of the target vehicle is as follows.

[0069] ω(t) = k·R(t) .

[0070] Among them k is the steering sensitivity coefficient, R(t) is the steering wheel angle.

[0071] Calculate the target vehicle speed. Decompose the target vehicle speed into x1, x Obtained on the 2-axis v x (t) and v y (t) , v x (t) The calculation formula is as follows.

[0072] v x (t) = v 2 (t)·cosγ(t) - a x (t)·Δt .

[0073] Among them, v 2 (t) Is the speed of the target vehicle at time t, and its initial value is v 2.

[0074] v y (t) The calculation formula is as follows.

[0075] v y (t) = v 2 (t)·sinγ(t) - a y (t)·Δt .

[0076] Calculate the interval time Δt After that, the displacement of the target vehicle. Decompose the position of the target vehicle to x 1, x Obtained on the 2-axis x ( t + Δt ) and y ( t + Δt ) 。x ( t + Δt ) The calculation formula is as follows.

[0077] x(t + Δt) = x(t) + v x (t + Δt)·Δt .

[0078] y ( t + Δt ) The calculation formula is as follows.

[0079] y(t + Δt) = y(t) + v y (t + Δt)·Δt .

[0080] Among them, x(t) 、 y(t)The initial values are all 0.

[0081] Finally, by determining whether the current position is the risk avoidance critical point. If any of the above 3 conditions is satisfied, the current position is not the risk avoidance critical point. Update γ ( t )、 x(t), y(t) The value of is t + Δt The value at time, update v 2 (t) The value of is . If none of the above 3 conditions are satisfied, the current position is the risk avoidance critical point and the algorithm iteration terminates. At termination, y cep Is the projected distance between the risk avoidance critical point and the pre-collision point on the x 2-axis, γ cep Is the included angle of the vehicle at the risk avoidance critical point, the critical distance m cep The calculation formula of is as follows.

[0082] m cep =y cep / sin (γ cep ) .

[0083] 3) Use the risk avoidance conditions in the fifth scenario with the minimum current vehicle distance as the goal to determine the risk avoidance distance in the fifth scenario, and calculate the risk avoidance time in the fifth scenario based on the risk avoidance distance in the fifth scenario; among them, the risk avoidance conditions in the fifth scenario are as follows.

[0084] y(t) ≤ y 0.

[0085] y(t + Δt) > y 0.

[0086] v 1 ·t - x 0 -x(t) > 0.5·d 2 +d 1 ·cosγ .

[0087] In the formula, d 1 is the width of the target vehicle, d 2 is the length of the vehicle to be avoided, x 0 is the initial distance between the target vehicle and the vehicle to be avoided in the second coordinate system in the x 2-axis direction, x(t) Is the target vehicle at t Time in the second coordinate system x The displacement passed in the 2-axis direction,γ is the included angle between the speed direction of the vehicle to be avoided and the speed direction of the target vehicle. v 1 is the speed of the target vehicle. Δt is the interval time.

[0088] 4) Using the risk avoidance conditions in the sixth scenario with the minimum current vehicle distance as the goal, determine the risk avoidance distance in the sixth scenario, and calculate the risk avoidance time in the sixth scenario based on the risk avoidance distance in the sixth scenario; among them, the risk avoidance conditions in the sixth scenario are as follows.

[0089] y(t) ≤ y 0.

[0090] y(t + Δt) > y 0.

[0091] x(t) - v 1 ·t + x 0 >0.5·d 2 +d 1 ·cosγ .

[0092] S3. As Figure 6 shown, calculate the successfully avoidable time according to the current target vehicle status data and the critical risk avoidance time T cep Calculate the successfully avoidable time.

[0093] Furthermore, the calculation formula for the successfully avoidable time is as follows.

[0094] T gap =T 0 -T cep .

[0095] T cep = m cep / v 0.

[0096] In the formula, T gap is the successfully avoidable time; T 0 is the total time from the current vehicle distance to the vehicle collision; T cep is the critical risk avoidance time; m cep is the vehicle distance from the critical risk avoidance point to the vehicle collision point; v 0 is the current vehicle speed of the target vehicle.

[0097] Optionally, when the successfully avoidable time T gap is less than 2 seconds, it is identified as a high-risk scenario.

[0098] In the actual application process, the successfully avoidable time is used to characterize the risk measurement index based on the critical state of risk avoidance. The longer the distance of the target vehicle from the risk avoidance critical point, the longer the time left for the autonomous driving to detect danger and perform risk avoidance operations, and the lower the risk of an accident. Conversely, the risk is higher.

[0099] S4. Use the successfully avoidable time to identify high-risk scenarios. When no high-risk scenario is identified, re-obtain the current vehicle distance. When a high-risk scenario is identified, use the passive safety cooperation strategy to perform passive safety constraints in stages; the high-risk scenario is a scenario where the successfully avoidable time is less than or equal to the preset time; the passive safety constraints include: seat belt constraint and / or airbag constraint.

[0100] Furthermore, as shown in Table 1, the passive safety cooperation strategy is as follows.

[0101] 1) When the successfully avoidable time is reduced to T cep the sum of the extended time slots, tighten the seat belt with the first pre-tightening force; the first pre-tightening force is 60% of the pre-tightening force of the target vehicle's seat belt.

[0102] 2) When the successfully avoidable time is reduced to T cep tighten the seat belt with the second pre-tightening force and pre-inflate the airbag. The second pre-tightening force is 100% of the pre-tightening force of the target vehicle's seat belt.

[0103] Table 1 Passive safety cooperation strategy table based on T cep

[0104]

[0105] Optionally, when the acceleration change of the current target vehicle exceeds the threshold, it indicates that a collision has occurred. At this time, the passive safety constraints also include: fully deploying the airbag and dynamically deflating the seat belt at the same time.

[0106] In the actual application process, compared with the existing high-risk scenario identification method based on the critical time to collision ( TTC ), the high-risk scenario identification method of the present application considers more comprehensive risk factors, and the used risk index T gap considers the randomness problems of the target vehicle going straight, turning left, and turning right during driving, and has better applicability to turning scenarios. In addition, T gap the index can distinguish TTC the risk differences that cannot be identified, so the high-risk scenario identification result is more accurate.

[0107] Through Tgap The risk level indicated by the value is used to determine whether it is a high-risk scenario, and the Pre-Crash dataset obtained in this application is used as the basis for scenario recognition. This dataset is formed by using accident reconstruction technology to reproduce the scenario before the accident and extracting the reproduced scenario data on the basis of obtaining on-site records from in-depth investigations of road traffic accidents in a certain country. The data after reconstruction mainly includes: the positions of the target vehicle and related vehicles, the running trajectories, the collision positions, the collision postures, the surrounding environment, etc. In this application, 116 car-vehicle-to-be-avoided collision accident scenarios in the dataset are randomly selected for research, and the scenarios are divided into two categories according to whether the target vehicle goes straight or turns before the accident.

[0108] Furthermore, when a high-risk scenario is recognized, it further includes: using a hierarchical braking strategy to perform safety braking in stages based on the current target vehicle state data, as follows.

[0109] 1) When the speed of the target vehicle is between 0 km / h ~ 30 km / h , primary braking is adopted; the primary braking is to brake with the first braking force when the available successful avoidance time is reduced to 2 T cep ; the first braking force is 100% of the braking force of the target vehicle.

[0110] 2) When the speed of the target vehicle is between 30 km / h ~50 km / h , secondary braking is adopted; the secondary braking is to brake with the second braking force when the available successful avoidance time is reduced to 4 T cep , and to brake with the first braking force when the available successful avoidance time is further reduced to 2 T cep ; the second braking force is 40% of the braking force of the target vehicle.

[0111] 3) When the speed of the target vehicle exceeds 50 km / h , tertiary braking is adopted; the tertiary braking is to issue a collision warning when the available successful avoidance time is reduced to 6 T cep , to brake with the second braking force when the available successful avoidance time is further reduced to 4 T cep , and to brake with the first braking force when the available successful avoidance time is further reduced to 2 T cep .

[0112] Among them, the hierarchical braking strategy of this embodiment is shown in Table 2.

[0113]

[0114] Optionally, when Tcep When it is less than 0.2 s, considering factors such as the driver's reaction time, the graded braking thresholds are set to 0.5 s and 1 s respectively.

[0115] The calculation results show that for most accident scenarios T gap the value is between 1.2 s and 2 s. For the scenario where the target vehicle is moving straight, there are some T gap less than 1 s. For the scenario where the target vehicle is turning T gap the value is concentrated between 1.4 s and 2 s, and for some scenarios it is about 1.5 s. Usually, when T gap it is less than 2 s, it is identified as a high-risk scenario.

[0116] In the actual application process, the graded braking strategy of this application takes into account factors such as the randomness problem during turning, etc., and the risk assessment is more accurate. Therefore, braking can be more timely, the speed curve is smoother, and accidents can be better avoided and injuries can be reduced. The effect is most obvious in the turning scenario.

[0117] At the same time, to verify the braking control strategy of this application, accident scenarios are built in the simulation environment, and simulation experiments are carried out to verify different collision scenarios, as follows.

[0118] First, the steps for building the simulation scenario are as follows.

[0119] (1) Import the accident reproduction file in the near-collision dataset (previously generated using PC-crash) into the Prescan simulation environment to generate a basic accident scenario.

[0120] (2) Improve the static environment in the basic accident scenario in the simulation environment.

[0121] (3) Realize the connection between Simulink and Prescan, and add a braking control algorithm module and a collision detection module in Simulink. Finally, build the simulation scenario and conduct a simulation test on the braking control algorithm. The simulation scenario is as Figure 7 shown.

[0122] The simulation results of the accident scenario where the target vehicle moving straight collides with the side of the vehicle to be avoided are as Figure 8 shown. It can be seen from the simulation speed and braking force change curves that the braking strategy of this application makes the vehicle speed curve change more smoothly, the braking lead is greater, the braking distance is smaller, and the risk avoidance ability and riding comfort in this scenario are better than the comparison strategy.

[0123] The simulation results of the accident scenario where the target vehicle moving straight rear-ends the vehicle to be avoided are as Figure 9As shown in the figure. Neither of the two braking strategies avoided the collision. However, compared with the comparative strategy, the braking strategy of the present application reduced the collision speed of the target vehicle from 39.9 km / h to 25.2 km / h, a decrease of 36.84%, reducing the harm caused by the accident.

[0124] The accident scenario simulation results of the target vehicle going straight and colliding with the oncoming vehicle to be avoided are as Figure 10 shown. The comparative control strategy failed to prevent the collision from occurring, and the target vehicle collided at a speed of 0.8 m / s. For such an extremely dangerous scenario, the braking strategy of the present application stopped the target vehicle within the first 1.8 seconds to avoid the accident.

[0125] The accident scenario simulation results of the target vehicle turning are as Figure 11 shown. Both braking strategies avoided the accident. The braking strategy of the present application has a more advanced braking time and a smoother speed curve, reducing the impact on the driver during the braking process.

[0126] It can be seen that the effectiveness of the braking strategy of the present application has been verified by high-risk scenario simulation experiments with different collision postures such as the target vehicle turning and the target vehicle going straight. The performance of the braking strategy of the present application in four types of scenarios exceeded the comparative strategy. The braking time was more advanced and the speed curve was smoother, which could better avoid accidents and reduce injuries. Especially in the turning scenario, the trigger time was advanced by about 2 s, and the effect was obvious.

[0127] The technical effects of the present application are as follows:

[0128] The present application first proposed the concept of the critical state of risk avoidance, and designed a calculation method for the critical point of risk avoidance for the target vehicle in two scenarios of going straight and turning, using the critical risk avoidance time to characterize the spatio-temporal proximity of the vehicle. By calculating the expected running time (the time for successful risk avoidance) of the target vehicle from the critical point of risk avoidance Tgap , the identification of high-risk scenarios is realized, the identification ability of the target vehicle for high-risk scenarios is improved, and corresponding passive safety cooperation strategies are formulated, which can initiate timely passive safety cooperation responses in high-risk scenarios, improve the safety factor of the target vehicle, and reduce the incidence of traffic accidents. In addition, the present application also formulates corresponding automatic driving braking strategies. The present application takes into account the risk avoidance ability of the target vehicle, is particularly applicable to the turning scenario; can distinguish the risk differences under different road adhesion coefficients; the formulated automatic driving braking strategy can intervene in advance, smooth the vehicle speed change and pre-start passive response, so as to effectively avoid accidents or reduce collision damage.

[0129] Using the critical avoidance time to characterize the spatio-temporal proximity of vehicles improves the target vehicle's recognition ability of high-risk scenarios, enables timely passive safety collaborative responses to be initiated in high-risk scenarios, improves the safety factor of the target vehicle, and reduces the incidence of traffic accidents.

[0130] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0131] Specific examples are used in this article to elaborate on the principles and implementation methods of this application. The descriptions of the above embodiments are only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for high-risk scenario recognition and passive safety collaboration based on a critical risk avoidance state, characterized in that The method for identifying high-risk scenarios and coordinating passive safety based on the critical avoidance state includes: Obtain the current target vehicle status data; the current target vehicle status data at least includes: the current driving state of the target vehicle, the current vehicle distance, the current speed of the target vehicle, and the current acceleration of the target vehicle; the current driving state of the target vehicle is straight or turning; the current vehicle distance is the distance between the target vehicle and the vehicle to be avoided. Determine the critical evasion time T based on the current target vehicle status data cep , which specifically includes: When the current driving state of the target vehicle is straight, calculate the avoidance time for each straight-ahead avoidance scenario using the avoidance conditions in different straight-ahead avoidance scenarios, and select the shortest time among the avoidance times for each straight-ahead avoidance scenario as the critical avoidance time Tcep; the straight-ahead avoidance scenarios at least include: the first scenario, the second scenario, and the third scenario; the first scenario is the scenario where the target vehicle decelerates to avoid the vehicle to be avoided; the second scenario is the scenario where the target vehicle turns in the same direction to avoid the vehicle to be avoided; the third scenario is the scenario where the target vehicle turns in the opposite direction to avoid the vehicle to be avoided. Among them, calculating the avoidance time for each straight-ahead avoidance scenario using the avoidance conditions in different straight-ahead avoidance scenarios specifically includes: Establish a first coordinate system with the moving direction of the target vehicle as the x1 axis, the direction perpendicular to the x1 axis as the x2 axis, and the current position of the target vehicle as the coordinate origin. Using the avoidance condition in the first scenario, with the minimum current vehicle distance as the goal, determine the avoidance distance in the first scenario, and calculate the avoidance time in the first scenario based on the avoidance distance in the first scenario; among them, the avoidance condition in the first scenario is as follows: v1 2 ≤v2 2 ·cos 2 θ + 2·a1·μ·g·m; In the formula, v1 is the speed of the target vehicle, v2 is the speed of the vehicle to be avoided, θ is the angle between the speed direction of the vehicle to be avoided and the x1 axis of the first coordinate system, a1 is the maximum acceleration of the target vehicle along the x1 axis, μ is the ground friction coefficient, g is the acceleration due to gravity, and m is the current vehicle distance. Using the avoidance condition in the second scenario, with the minimum current vehicle distance as the goal, determine the avoidance distance in the second scenario, and calculate the avoidance time in the second scenario based on the avoidance distance in the second scenario; among them, the avoidance condition in the second scenario is as follows: v1 2 ≤v2 2 ·cos 2 θ + 2·a1·μ·g·m; Lx1 - d1 / 2 - (d2·sinθ) / 2 + a ≥ Lx2; In the formula, d1 is the width of the target vehicle, d2 is the length of the vehicle to be avoided, Lx1 is the lateral displacement of the vehicle, Lx2 is the lateral displacement of the vehicle to be avoided, and a is the perpendicular distance between the vehicle to be avoided and the x1 axis of the first coordinate system. Using the avoidance condition in the third scenario, with the minimum current vehicle distance as the goal, determine the avoidance distance in the third scenario, and calculate the avoidance time in the third scenario based on the avoidance distance in the third scenario; among them, the avoidance condition in the third scenario is as follows: v1 2 ≤v2 2 ·cos 2 θ + 2·a1·μ·g·m; Lx1 + Lx2 ≤ a - d1 / 2 - (d2·sinθ) / 2; The critical avoidance time T cep is the time from the critical avoidance point to the time when the target vehicle and the vehicle to be avoided are about to collide; the critical avoidance point is the shortest distance required for the target vehicle to successfully avoid the vehicle to be avoided. Based on the current target vehicle status data and the critical avoidance time T cep Calculate the successfully avoidable time; Identify high-risk scenarios using the available successful avoidance time. When no high-risk scenario is identified, re-acquire the current vehicle distance. When a high-risk scenario is identified, use the passive safety cooperation strategy to perform passive safety constraints in stages; the high-risk scenario is a scenario where the available successful avoidance time is less than or equal to a preset time; the passive safety constraints include: seat belt constraint and / or airbag constraint.

2. The method for identifying high-risk scenarios and passive safety collaboration based on critical risk avoidance states according to claim 1, wherein Determine the critical hazard avoidance time T based on the current target vehicle state data cep , which specifically includes: When the current driving state of the target vehicle is steering, calculate the evasion time for each steering evasion scenario using the evasion conditions in different steering evasion scenarios, and select the shortest time among the evasion times for each steering evasion scenario as the critical evasion time T cep ; The steering evasion scenarios at least include: the fourth scenario, the fifth scenario, and the sixth scenario; the fourth scenario is a scenario where the target vehicle has decelerated to 0 in the driving direction of the vehicle to be avoided before the target vehicle reaches the driving route of the vehicle to be avoided; the fifth scenario is a scenario where the target vehicle passes through the driving route of the vehicle to be avoided from behind the vehicle to be avoided and then continues to drive behind the vehicle to be avoided; the sixth scenario is a scenario where the target vehicle passes through the driving route of the vehicle to be avoided in front of the vehicle to be avoided and then continues to drive in front of the vehicle to be avoided.

3. The method for identifying high-risk scenarios and passive safety collaboration based on critical risk avoidance states according to claim 2, wherein Calculate the avoidance time for each steering avoidance scenario using the avoidance conditions in different steering avoidance scenarios, specifically including: Establish a second coordinate system with the moving direction of the vehicle to be avoided as the x1 axis, the direction perpendicular to the x1 axis as the x2 axis, and the current position of the vehicle to be avoided as the coordinate origin. Using the avoidance conditions in the fourth scenario, with the minimum current vehicle distance as the goal, determine the avoidance distance in the fourth scenario, and calculate the avoidance time in the fourth scenario based on the avoidance distance in the fourth scenario; among them, the avoidance conditions in the fourth scenario are as follows: v y (t) = 0; y(t) ≤ y0; where v y (t) is the speed of the target vehicle in the x1-axis direction in the second coordinate system at time t, y(t) is the displacement passed by the target vehicle in the x1-axis direction in the second coordinate system at time t, and y0 is the initial distance between the target vehicle and the vehicle to be avoided in the x1-axis direction in the second coordinate system; Using the avoidance conditions in the fifth scenario, with the minimum current vehicle distance as the goal, determine the avoidance distance in the fifth scenario, and calculate the avoidance time in the fifth scenario based on the avoidance distance in the fifth scenario; among them, the avoidance conditions in the fifth scenario are as follows: y(t) ≤ y0; y(t + Δt) > y0; v1·t - x0 - x(t) > 0.5·d2 + d1·cosγ; In the formula, d1 is the width of the target vehicle, d2 is the length of the vehicle to be avoided, x0 is the initial distance between the target vehicle and the vehicle to be avoided in the x2 axis direction in the second coordinate system, x(t) is the displacement passed by the target vehicle in the x2 axis direction in the second coordinate system at time t, γ is the included angle between the speed direction of the vehicle to be avoided and the speed direction of the target vehicle, v1 is the speed of the target vehicle, and Δt is the interval time; Using the avoidance conditions in the sixth scenario, with the minimum current vehicle distance as the goal, determine the avoidance distance in the sixth scenario, and calculate the avoidance time in the sixth scenario based on the avoidance distance in the sixth scenario; among them, the avoidance conditions in the sixth scenario are as follows: y(t) ≤ y0; y(t + Δt) > y0; x(t) - v1·t + x0 > 0.5·d2 + d1·cosγ.

4. The method for identifying high-risk scenarios and passive safety coordination based on the critical risk avoidance state according to claim 3, characterized in that, The calculation formula for the available successful avoidance time is as follows: T gap = T0 - T cep ; T cep = m cep / v0; Where T gap is the successful risk avoidance time; T0 is the total time from the current vehicle distance to the vehicle collision; T cep is the critical risk avoidance time; m cep is the vehicle distance from the critical risk avoidance point to the vehicle collision point; v0 is the current vehicle speed of the target vehicle.

5. The method for identifying high-risk scenarios and passive safety collaboration based on critical risk avoidance states according to claim 1, wherein The passive safety cooperation strategy specifically includes: When the time for successful risk avoidance is reduced to T cep and the sum of the extended time slots, tighten the seat belt with the first pre-tightening force; When the available successful risk avoidance time is reduced to T cep the seat belt is tightened with a second pre-tightening force and the airbag is pre-inflated.

6. The method for identifying high-risk scenarios and passive safety collaboration based on the critical risk avoidance state according to claim 5, wherein The first pre-tightening force is 60% of the pre-tightening force of the seat belt of the target vehicle; the second pre-tightening force is 100% of the pre-tightening force of the seat belt of the target vehicle.

7. The method for high-risk scenario recognition and passive safety collaboration based on critical risk avoidance state according to claim 1, wherein When a high-risk scenario is identified, it also includes: performing safety braking in stages using a hierarchical braking strategy based on the current target vehicle state data.

8. The method for identifying high-risk scenarios and passive safety collaboration based on the critical risk avoidance state according to claim 7, characterized in that Performing safety braking in stages using a hierarchical braking strategy based on the current target vehicle state data, specifically including: When the target vehicle speed is between 0 km / h and 30 km / h, primary braking is adopted; the primary braking is to brake with the first braking force when the available avoidance time is reduced to 2T cep seconds. When the target vehicle speed is between 30 km / h and 50 km / h, secondary braking is adopted; the secondary braking is that when the available successful avoidance time is reduced to 4T cep , brake with the second braking force, and when the available successful avoidance time continues to be reduced to 2T cep , brake with the first braking force; When the speed of the target vehicle exceeds 50 km / h, three-stage braking is adopted; the three-stage braking means that when the available successful avoidance time is reduced to 6T cep a collision warning is issued; when the available successful avoidance time continues to be reduced to 4T cep braking is performed with the second braking force; when the available successful avoidance time continues to be reduced to 2T cep braking is performed with the first braking force.

9. The method for identifying high-risk scenarios and passive safety collaboration based on critical risk avoidance states according to claim 8, wherein The first braking force is 100% of the braking force of the target vehicle; the second braking force is 40% of the braking force of the target vehicle.

Images