Method and device for determining low-speed emergency braking and electronic equipment

Abstract

According to the low-speed emergency braking determination method and device and the electronic equipment, the collision sensitive width corresponding to each discrete track is calculated based on the track confidence coefficient, so that the collision sensitive width of the discrete track with the low track confidence coefficient can be tightened, more attention is paid to a central area, the surrounding area of a vehicle is divided, and the reliability of the vehicle is improved. According to the method and the device, the target division areas in which collision possibly occurs are determined from the division areas obtained through division, the subsequent calculation amount is reduced, the obstacle position coefficients are set for the target obstacles in the target division areas, calculation of the target collision coefficient corresponding to each target obstacle is realized based on the collision sensitive width corresponding to each discrete track, and the collision accuracy is improved. According to the obstacle position coefficient of each target obstacle and the target collision coefficient corresponding to the obstacle position coefficient, the risk coefficient of each target obstacle relative to the target discrete trajectory is calculated, and whether the collision risk exists is determined based on the risk coefficient, so that the finally determined emergency braking opportunity is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of assisted driving, and in particular to a method, device and electronic equipment for determining low-speed emergency braking. Background Art

[0002] Low-speed emergency braking (MEB) is a sub-function in the field of L2 assisted driving. The function generally takes effect when the vehicle speed does not exceed 12km / h. In scenes such as parking, turning, and passing through narrow spaces, it identifies the risks of obstacles around the vehicle. When there is a risk of collision, it intervenes with the vehicle's brakes to avoid a collision, thereby ensuring the safety of the driver and the vehicle.

[0003] Since MEB is an active safety function, it is activated by manual driving. Compared with the AEB (automatic emergency braking) function at higher speeds, there will be frequent acceleration and deceleration and rapid steering wheel rotation when driving at low speeds.

[0004] The traditional implementation method is to predict the driving trajectory based on the current vehicle state, and combine it with the obstacle position detected by the sensor, use the vehicle kinematics formula to calculate the collision time, and when the collision time is less than the threshold, trigger the vehicle emergency braking.

[0005] Since it is difficult for the driver to understand the operating intention in low-speed scenarios, it is difficult to predict the movement trend of the vehicle when acceleration or deceleration or rapid steering wheel rotation occurs. In addition, during rapid steering of the vehicle, the perception accuracy of obstacles will decrease (obstacle angle, outer contour size, etc.). The above two factors will lead to a large number of "misbraking" or "missed braking".

[0006] In summary, how to improve the accuracy of low-speed emergency braking has become a technical problem that urgently needs to be solved. Summary of the invention

[0007] In view of this, an object of the present invention is to provide a method, device and electronic device for determining low-speed emergency braking to alleviate the technical problem of poor accuracy of existing low-speed emergency braking.

[0008] In a first aspect, an embodiment of the present invention provides a method for determining low-speed emergency braking, comprising:

[0009] Calculating, according to the current state information of the vehicle, discrete trajectories of the vehicle at each discrete time point within a preset future time and trajectory confidences corresponding to each discrete trajectory, and calculating, according to each trajectory confidence and the width of the vehicle, a collision-sensitive width corresponding to each discrete trajectory, wherein the time intervals between adjacent discrete time points are the same;

[0010] Dividing the surrounding area of ​​the current position of the vehicle, and determining a target divided area where a collision may occur in the divided areas according to the driving direction of the vehicle;

[0011] Setting an obstacle position coefficient for each target obstacle in the target divided area according to the distance between the target obstacle and the vehicle to obtain an obstacle position coefficient for each target obstacle;

[0012] Calculating a collision coefficient between each of the target obstacles and each of the discrete trajectories based on a collision-sensitive width corresponding to each of the discrete trajectories, and determining a target collision coefficient corresponding to each of the target obstacles according to the collision coefficient between each of the target obstacles and each of the discrete trajectories;

[0013] Calculating a risk coefficient of each target obstacle relative to a target discrete trajectory according to an obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, wherein the target discrete trajectory is a discrete trajectory corresponding to the target collision coefficient;

[0014] Determining whether each of the target obstacles has a collision risk with the target discrete trajectory based on a risk coefficient of each of the target obstacles with respect to the target discrete trajectory;

[0015] If there is a collision risk, an emergency braking timing is determined according to the performance of the vehicle and a target discrete trajectory with a collision risk.

[0016] Furthermore, the discrete trajectories of the vehicle at each discrete time point in a preset future time and the trajectory confidences corresponding to each discrete trajectory are calculated based on the current state information of the vehicle, including:

[0017] Calculate the formula HeadAng based on the vehicle head angle [i] =HeadAng [i-1] +YawRate*T calculates the head angle of the vehicle at each discrete time point in the future preset time, where HeadAng [i] HeadAng represents the head angle of the vehicle at the i-th discrete time point in the future preset time. [i-1] represents the head angle of the vehicle at the (i-1)th discrete time point in the future preset time, YawRate represents the angular velocity in the current state information, T represents the time interval, when i is 1, HeadAng [i-1] Indicates the current vehicle head angle in the current state information;

[0018] Calculate the formula X based on the vehicle's X coordinate [i] =X [i-1] +V [i] *cos(HeadAng[i] )*T calculates the x coordinates of the vehicle at each discrete time point in the future preset time, where X [i] represents the X coordinate of the vehicle at the i-th discrete time point in the future preset time, X [i-1] represents the x-coordinate of the vehicle at the (i-1)th discrete time point in the future preset time, V [i] HeadAng represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i] represents the front angle of the vehicle at the i-th discrete time point in the future preset time, T represents the time interval, when i is 1, X [i-1] represents the current X coordinate of the vehicle in the current state information;

[0019] Calculate the formula Y based on the vehicle's Y coordinate [i] =Y [-1] +V [i] *sin(HeadAng [i] )*T calculates the Y coordinate of the vehicle at each discrete time point in the future preset time, where Y [i] represents the Y coordinate of the vehicle at the i-th discrete time point in the future preset time, Y [i-1] represents the Y coordinate of the vehicle at the (i-1)th discrete time point in the future preset time, V [i] HeadAng represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i] represents the front angle of the vehicle at the i-th discrete time point in the future preset time, T represents the time interval, when i is 1, Y [i-1] represents the current Y coordinate of the vehicle in the current state information;

[0020] The front angle of the vehicle at each discrete time point in the future preset time, the X coordinate of the vehicle at each discrete time point in the future preset time, and the Y coordinate of the vehicle at each discrete time point in the future preset time are used as discrete trajectories of the vehicle at each discrete time point in the future preset time;

[0021] According to the trajectory confidence calculation formula Confidence [i] =A1*(Distance Pred -Distance [i] ) / Distance Pred +A2*(Lgt AccMax -Lgt Acc ) / Lgt AccMax +A3*(Steer SpdMax -Steer Spd) / Steer SpdMax

[0022] Calculate the trajectory confidence corresponding to each discrete trajectory, where Confidence [i] Represents the trajectory confidence of the discrete trajectory at the i-th discrete time point, Distance Pred Indicates the total length of the discrete trajectory corresponding to the current state information, Distance [i] represents the length of the discrete trajectory at the ith discrete time point, Lgt AccMax Indicates the maximum longitudinal acceleration, Lgt Acc Indicates the longitudinal acceleration in the current state information, Steer SpdMax Indicates the maximum rotation speed of the steering wheel, Steer Spd represents the rotation speed of the steering wheel in the current state information, and A1, A2, and A3 represent preset weight coefficients;

[0023] Calculating the collision sensitive width corresponding to each discrete trajectory according to the trajectory confidence and the width of the vehicle, including:

[0024] The collision-sensitive width corresponding to each discrete trajectory is calculated according to the collision-sensitive width calculation formula: collision-sensitive width=vehicle width×trajectory confidence.

[0025] Furthermore, dividing the surrounding area of ​​the current position of the vehicle includes:

[0026] Dividing the surrounding area of ​​the vehicle into six divided areas according to a horizontal line of a front bumper, a horizontal line of a rear axle, and a horizontal line of a rear bumper of the vehicle;

[0027] Setting an obstacle position coefficient for each target obstacle in the target divided area according to the distance between the target obstacle and the vehicle includes:

[0028] If the distance between a first target obstacle among the target obstacles and the vehicle is not greater than a first preset distance, setting an obstacle position coefficient of the first target obstacle to 1;

[0029] If the distance between a second target obstacle among the target obstacles and the vehicle is greater than the first preset distance and less than the second preset distance, the obstacle position coefficient of the second target obstacle is set according to a preset decreasing rule, wherein the preset decreasing rule is that when the distance is between the first preset distance and the second preset distance, the obstacle position coefficient is linearly decreased from 1 to 0 from near to far;

[0030] If the distance between a third target obstacle among the target obstacles and the vehicle is greater than the second preset distance, the obstacle position coefficient of the third target obstacle is set to 0.

[0031] Further, calculating the collision coefficient between each of the target obstacles and each of the discrete trajectories based on the collision sensitive width corresponding to each of the discrete trajectories, and determining the target collision coefficient corresponding to each of the target obstacles according to the collision coefficient between each of the target obstacles and each of the discrete trajectories, including:

[0032] The collision coefficient between each target obstacle and each discrete track is calculated according to the collision coefficient calculation formula Collision_Coe=CE / AE, wherein Collision_Coe represents the collision coefficient between one target obstacle and one discrete track, CE represents the overlapping width between the target obstacle and the discrete track, and AE represents half of the collision sensitive width corresponding to the discrete track:

[0033] The maximum collision coefficient among the collision coefficients between each target obstacle and each discrete trajectory is used as the target collision coefficient corresponding to each target obstacle.

[0034] Further, the risk coefficient of each target obstacle relative to the target discrete trajectory is calculated according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, including:

[0035] The risk coefficient of each target obstacle relative to the target discrete trajectory is calculated according to the risk coefficient calculation formula: risk coefficient = obstacle position coefficient × target collision coefficient.

[0036] Further, determining whether each target obstacle has a collision risk with the target discrete trajectory based on the risk coefficient of each target obstacle with respect to the target discrete trajectory includes:

[0037] If the risk coefficient is greater than a preset risk threshold, it is determined that the corresponding target obstacle has a collision risk with the target discrete trajectory.

[0038] Furthermore, the performance of the vehicle includes: the time required for the vehicle to complete braking, and the emergency braking timing is determined according to the performance of the vehicle and the target discrete trajectory with collision risk, including:

[0039] Determining a time when the vehicle will collide in the future based on the target discrete trajectory with collision risk;

[0040] The emergency braking timing is determined according to the time required for the vehicle to complete braking and the time when the vehicle will collide in the future.

[0041] In a second aspect, an embodiment of the present invention further provides a low-speed emergency braking determination device, comprising:

[0042] a first calculation unit, configured to calculate, according to current state information of the vehicle, discrete trajectories of the vehicle at discrete time points within a preset future time and trajectory confidences corresponding to the discrete trajectories, and to calculate, according to the trajectory confidences and the width of the vehicle, a collision-sensitive width corresponding to the discrete trajectories, wherein time intervals between adjacent discrete time points are the same;

[0043] a dividing and determining unit, configured to divide the surrounding area of ​​the current position of the vehicle, and determine a target divided area where a collision may occur in the divided areas according to the driving direction of the vehicle;

[0044] a setting unit, configured to set an obstacle position coefficient for each target obstacle according to the distance between the target obstacle and the vehicle in the target divided area, so as to obtain an obstacle position coefficient for each target obstacle;

[0045] a calculation and determination unit, configured to calculate a collision coefficient between each of the target obstacles and each of the discrete trajectories based on a collision-sensitive width corresponding to each of the discrete trajectories, and determine a target collision coefficient corresponding to each of the target obstacles according to the collision coefficient between each of the target obstacles and each of the discrete trajectories;

[0046] A second calculation unit is used to calculate a risk coefficient of each target obstacle relative to a target discrete trajectory according to an obstacle position coefficient of each target obstacle and a target collision coefficient corresponding thereto, wherein the target discrete trajectory is a discrete trajectory corresponding to the target collision coefficient;

[0047] A first determination unit is used to determine whether each of the target obstacles has a collision risk with the target discrete trajectory based on a risk coefficient of each of the target obstacles with respect to the target discrete trajectory;

[0048] The second determination unit is configured to determine an emergency braking timing according to the performance of the vehicle and a target discrete trajectory with a collision risk if there is a collision risk.

[0049] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described in the first aspect when executing the computer program.

[0050] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to execute any method described in the first aspect above.

[0051] In an embodiment of the present invention, a method for determining low-speed emergency braking is provided, comprising: calculating discrete trajectories of the vehicle at each discrete time point within a preset time in the future and trajectory confidences corresponding to each discrete trajectory based on current state information of the vehicle, and calculating collision-sensitive widths corresponding to each discrete trajectory based on each trajectory confidence and the width of the vehicle, wherein the time intervals between adjacent discrete time points are the same; dividing the surrounding area of ​​the current position of the vehicle, and determining a target divided area where a collision may occur in the divided areas obtained according to the driving direction of the vehicle; setting an obstacle position coefficient for each target obstacle according to the distance between the target obstacle in the target divided area and the vehicle, and obtaining an obstacle coefficient for each target obstacle. position coefficient; calculating the collision coefficient of each target obstacle with each discrete trajectory based on the collision sensitive width corresponding to each discrete trajectory, and determining the target collision coefficient corresponding to each target obstacle according to the collision coefficient of each target obstacle with each discrete trajectory; calculating the risk coefficient of each target obstacle relative to the target discrete trajectory according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, wherein the target discrete trajectory is the discrete trajectory corresponding to the target collision coefficient; determining whether each target obstacle has a collision risk with the target discrete trajectory based on the risk coefficient of each target obstacle relative to the target discrete trajectory; if there is a collision risk, determining the emergency braking timing according to the performance of the vehicle and the target discrete trajectory with the collision risk. It can be seen from the above description that in the method for determining low-speed emergency braking of the present invention, the credibility of each discrete trajectory is characterized by the trajectory confidence, and the collision sensitive width corresponding to each discrete trajectory is calculated based on the trajectory confidence, so that the collision sensitive width of the discrete trajectory with low trajectory confidence can be tightened, thereby paying more attention to the central area, improving accuracy, and avoiding "false braking". In addition, the surrounding area of ​​the current position of the vehicle is divided into regions, and the target divided area where the collision may occur is determined from the divided divided areas, and the calculation of obstacles in the divided areas that have no effect on the movement of the vehicle is abandoned, reducing the subsequent calculation amount, and setting an obstacle position coefficient for the target obstacle in the target divided area to characterize the detection accuracy of the sensor. Finally, based on the collision sensitive width corresponding to each discrete trajectory, the calculation of the target collision coefficient corresponding to each target obstacle is realized, and according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, the calculation of the risk coefficient of each target obstacle relative to the target discrete trajectory is realized, and whether there is a collision risk is determined based on the risk coefficient. The above collision risk determination process is more in line with the law of nature, so that the final determined emergency braking timing is more accurate, alleviating the technical problem of poor accuracy of the existing low-speed emergency braking. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A flowchart of a method for determining low-speed emergency braking provided by an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of calculating the collision sensitive width corresponding to each discrete trajectory provided by an embodiment of the present invention;

[0055] Figure 3 A schematic diagram of six divided areas provided in an embodiment of the present invention;

[0056] Figure 4 A schematic diagram of setting an obstacle position coefficient provided by an embodiment of the present invention;

[0057] Figure 5 A schematic diagram of calculating a collision coefficient provided by an embodiment of the present invention;

[0058] Figure 6 A schematic diagram of a low-speed emergency braking determination device provided by an embodiment of the present invention;

[0059] Figure 7 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] Conventional low-speed emergency braking has poor accuracy.

[0062] Based on this, in the method for determining low-speed emergency braking of the present invention, the credibility of each discrete trajectory is characterized by the trajectory confidence, and the collision sensitive width corresponding to each discrete trajectory is calculated based on the trajectory confidence, so that the collision sensitive width of the discrete trajectory with low trajectory confidence can be tightened, thereby paying more attention to the central area, improving accuracy, and avoiding "false braking". In addition, the surrounding area of ​​the current position of the vehicle is divided into regions, and the target divided area where the collision may occur is determined from the divided divided areas, and the calculation of obstacles in the divided areas that have no effect on the movement of the vehicle is abandoned, reducing the subsequent calculation amount, and setting an obstacle position coefficient for the target obstacle in the target divided area to characterize the detection accuracy of the sensor. Finally, based on the collision sensitive width corresponding to each discrete trajectory, the calculation of the target collision coefficient corresponding to each target obstacle is realized, and according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, the calculation of the risk coefficient of each target obstacle relative to the target discrete trajectory is realized, and whether there is a collision risk is determined based on the risk coefficient. The above collision risk determination process is more in line with natural laws, so that the final determined emergency braking timing is more accurate.

[0063] To facilitate understanding of this embodiment, a method for determining low-speed emergency braking disclosed in an embodiment of the present invention is first introduced in detail.

[0064] Embodiment 1:

[0065] According to an embodiment of the present invention, an embodiment of a method for determining low-speed emergency braking is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0066] Figure 1 is a flow chart of a method for determining low-speed emergency braking according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0067] Step S102, calculating the discrete trajectories of the vehicle at each discrete time point in a preset future time and the trajectory confidence corresponding to each discrete trajectory according to the current state information of the vehicle, and calculating the collision sensitive width corresponding to each discrete trajectory according to the trajectory confidence and the width of the vehicle, wherein the time intervals between adjacent discrete time points are the same;

[0068] In an embodiment of the present invention, the above-mentioned future preset time may be within the next 5 seconds, and the time interval between the above-mentioned adjacent discrete time points may be 100 ms, that is, there is a discrete trajectory corresponding to every 100 ms in the next 5 seconds. In this way, 50 discrete trajectories can be obtained in the end. The embodiment of the present invention does not limit the specific values ​​of the above-mentioned parameters.

[0069] The above-mentioned trajectory confidence is used to characterize the credibility of the corresponding discrete trajectory. After obtaining the trajectory confidence, the collision sensitive width corresponding to each discrete trajectory can be calculated according to the trajectory confidence, so that the collision sensitive width of the discrete trajectory with low trajectory confidence is tightened, thereby paying more attention to the central area, improving accuracy, and avoiding "false braking". The process will be described in detail below and will not be repeated here.

[0070] Step S104, dividing the surrounding area of ​​the current position of the vehicle, and determining a target divided area where a collision may occur in the divided areas according to the driving direction of the vehicle;

[0071] Step S106, setting an obstacle position coefficient for each target obstacle according to the distance between the target obstacle and the vehicle in the target division area, to obtain an obstacle position coefficient for each target obstacle;

[0072] Specifically, the target obstacle can be detected by a sensor (such as an ultrasonic sensor, a surround view camera), and the obstacle information detected essentially includes: the size of the obstacle and the angle of the obstacle. Since the detection accuracy of the sensor is limited, the closer the obstacle is to the vehicle, the more accurate the detection is. Therefore, an obstacle position coefficient is set for each target obstacle according to the distance between the target obstacle and the vehicle. The obstacle position coefficient of each target obstacle is used to characterize the detection accuracy of the corresponding sensor, thereby improving the accuracy of subsequent collision detection.

[0073] Step S108, calculating a collision coefficient between each target obstacle and each discrete trajectory based on the collision sensitive width corresponding to each discrete trajectory, and determining a target collision coefficient corresponding to each target obstacle according to the collision coefficient between each target obstacle and each discrete trajectory;

[0074] Step S110, calculating a risk coefficient of each target obstacle relative to a target discrete trajectory according to an obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, wherein the target discrete trajectory is a discrete trajectory corresponding to the target collision coefficient;

[0075] Specifically, the risk coefficient not only takes into account the target collision coefficient, but also takes into account the obstacle position coefficient of the target obstacle, that is, the detection accuracy of the sensor is also taken into account, which further improves the accuracy of the calculated risk coefficient.

[0076] Step S112, determining whether each target obstacle has a collision risk with the target discrete trajectory based on the risk coefficient of each target obstacle with respect to the target discrete trajectory;

[0077] Specifically, compared with the determination process of a binary system, this process is more in line with natural laws, and the determined collision risk is more accurate and reliable.

[0078] Step S114: if there is a collision risk, determining the emergency braking timing according to the vehicle performance and the target discrete trajectory with the collision risk.

[0079] In an embodiment of the present invention, a method for determining low-speed emergency braking is provided, comprising: calculating discrete trajectories of the vehicle at each discrete time point within a preset time in the future and trajectory confidences corresponding to each discrete trajectory based on current state information of the vehicle, and calculating collision-sensitive widths corresponding to each discrete trajectory based on each trajectory confidence and the width of the vehicle, wherein the time intervals between adjacent discrete time points are the same; dividing the surrounding area of ​​the current position of the vehicle, and determining a target divided area where a collision may occur in the divided areas obtained according to the driving direction of the vehicle; setting an obstacle position coefficient for each target obstacle according to the distance between the target obstacle in the target divided area and the vehicle, and obtaining an obstacle coefficient for each target obstacle. position coefficient; calculating the collision coefficient of each target obstacle with each discrete trajectory based on the collision sensitive width corresponding to each discrete trajectory, and determining the target collision coefficient corresponding to each target obstacle according to the collision coefficient of each target obstacle with each discrete trajectory; calculating the risk coefficient of each target obstacle relative to the target discrete trajectory according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, wherein the target discrete trajectory is the discrete trajectory corresponding to the target collision coefficient; determining whether each target obstacle has a collision risk with the target discrete trajectory based on the risk coefficient of each target obstacle relative to the target discrete trajectory; if there is a collision risk, determining the emergency braking timing according to the performance of the vehicle and the target discrete trajectory with the collision risk. It can be seen from the above description that in the method for determining low-speed emergency braking of the present invention, the credibility of each discrete trajectory is characterized by the trajectory confidence, and the collision sensitive width corresponding to each discrete trajectory is calculated based on the trajectory confidence, so that the collision sensitive width of the discrete trajectory with low trajectory confidence can be tightened, thereby paying more attention to the central area, improving accuracy, and avoiding "false braking". In addition, the surrounding area of ​​the current position of the vehicle is divided into regions, and the target divided area where the collision may occur is determined from the divided divided areas, and the calculation of obstacles in the divided areas that have no effect on the movement of the vehicle is abandoned, reducing the subsequent calculation amount, and setting an obstacle position coefficient for the target obstacle in the target divided area to characterize the detection accuracy of the sensor. Finally, based on the collision sensitive width corresponding to each discrete trajectory, the calculation of the target collision coefficient corresponding to each target obstacle is realized, and according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, the calculation of the risk coefficient of each target obstacle relative to the target discrete trajectory is realized, and whether there is a collision risk is determined based on the risk coefficient. The above collision risk determination process is more in line with the law of nature, so that the final determined emergency braking timing is more accurate, alleviating the technical problem of poor accuracy of the existing low-speed emergency braking.

[0080] The above content briefly introduces the determination method of low-speed emergency braking of the present invention, and the specific contents involved are described in detail below.

[0081] In an optional embodiment of the present invention, the discrete trajectories of the vehicle at each discrete time point in a preset future time and the trajectory confidence corresponding to each discrete trajectory are calculated according to the current state information of the vehicle, which specifically includes the following steps:

[0082] (1) Calculate the formula HeadAng based on the vehicle head angle [i] =HeadAng [i-1] +YawRate*T calculates the head angle of the vehicle at each discrete time point in the future preset time, where HeadAng [i] HeadAng represents the vehicle's head angle at the i-th discrete time point in the future preset time. [i-1] It represents the head angle of the vehicle at the (i-1)th discrete time point in the future preset time, YawRate represents the angular velocity in the current state information, T represents the time interval, and when i is 1, HeadAng [i-1] Indicates the current vehicle head angle in the current status information;

[0083] Specifically, the time interval is 100 ms as in the above step S102.

[0084] (2) Calculate the formula X based on the vehicle's X coordinate [i] =X [i-1] +V [i] *cos(HeadAng [i] )*T calculates the x coordinates of the vehicle at each discrete time point in the future preset time, where X [i] represents the X coordinate of the vehicle at the i-th discrete time point in the future preset time, X [i-1] represents the X coordinate of the vehicle at the (i-1)th discrete time point in the future preset time, V [i] HeadAng represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i] represents the vehicle's front angle at the i-th discrete time point in the future preset time, T represents the time interval, when i is 1, X [i-1] Indicates the current x-coordinate of the vehicle in the current state information;

[0085] Specifically, V [i] =V [i-1] +Lgt Acc *T, where V [i] V represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i-1] Indicates the speed of the vehicle at the (i-1)th discrete time point in the future preset time, Lgt Acc represents the longitudinal acceleration in the current state information, T represents the time interval, when i is 1, V[i-1] Indicates the current speed of the vehicle in the current status information.

[0086] (3) Calculate the formula Y based on the vehicle's Y coordinate [i] =Y [i-1] +V [i] *sin(HeadAng [i] )*T calculates the Y coordinate of the vehicle at each discrete time point in the future preset time, where Y [i] represents the Y coordinate of the vehicle at the i-th discrete time point in the future preset time, Y [i-1] represents the Y coordinate of the vehicle at the (i-1)th discrete time point in the future preset time, V [i] HeadAng represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i] represents the vehicle's front angle at the i-th discrete time point in the future preset time, T represents the time interval, when i is 1, Y [i-1] Indicates the current Y coordinate of the vehicle in the current state information;

[0087] Specifically, V [i] =V [i-1] +Lgt Acc *T, where V [i] V represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i-1] Indicates the speed of the vehicle at the (i-1)th discrete time point in the future preset time, Lgt Acc represents the longitudinal acceleration in the current state information, T represents the time interval, when i is 1, V [i-1] Indicates the current speed of the vehicle in the current status information.

[0088] (4) The front angle of the vehicle at each discrete time point in the future preset time, the X coordinate of the vehicle at each discrete time point in the future preset time, and the Y coordinate of the vehicle at each discrete time point in the future preset time are used as the discrete trajectory of the vehicle at each discrete time point in the future preset time;

[0089] (5) Calculate the trajectory confidence formula [i] =A1*(Distance Pred -Distance [i] ) / Distance Pred +A2*(Lgt AccMax -Lgt Acc ) / Lgt AccMax +A3*(Steer SpdMax -Steer Spd ) / Steer SpdMax

[0090] Calculate the trajectory confidence corresponding to each discrete trajectory, where Confidence [i] Represents the trajectory confidence of the discrete trajectory at the i-th discrete time point, Distance Pred Indicates the total length of the discrete trajectory corresponding to the current state information, Distance [i] represents the length of the discrete trajectory at the ith discrete time point, Lgt AccMax Indicates the maximum longitudinal acceleration, Lgt Acc Indicates the longitudinal acceleration in the current state information, Steer SpdMax Indicates the maximum rotation speed of the steering wheel, Steer Spd Indicates the rotation speed of the steering wheel in the current state information, and A1, A2, and A3 represent preset weight coefficients;

[0091] Specifically, the trajectory confidence has three weight dimensions. The first dimension is related to the distance, that is, the longer the predicted driving distance, the lower the trajectory confidence; the second dimension is related to the longitudinal acceleration, that is, the greater the absolute value of the longitudinal acceleration of the vehicle, the lower the trajectory confidence; the third dimension is related to the steering wheel rotation speed, that is, the greater the absolute value of the steering wheel rotation speed, the lower the trajectory confidence. Through the above three atoms, the trajectory confidence calculation formula is designed, that is, the farther the discrete trajectory, the greater the acceleration and deceleration, and the greater the steering wheel speed, the smaller the trajectory confidence, that is, the longer the distance, the greater the acceleration and deceleration, and the faster the steering wheel speed, the lower the credibility of the predicted discrete trajectory. The three dimensions are associated with the three weight coefficients A1, A2 and A3, so that the output trajectory confidence range is between [0, 1].

[0092] In an optional embodiment of the present invention, the collision sensitive width corresponding to each discrete trajectory is calculated according to the confidence of each trajectory and the width of the vehicle, which specifically includes the following steps:

[0093] The collision-sensitive width corresponding to each discrete trajectory is calculated according to the collision-sensitive width calculation formula: collision-sensitive width = vehicle width × trajectory confidence.

[0094] Specifically, Figure 2 As shown in the figure, the arrow direction is the vehicle's driving direction, the leftmost rectangular box is the vehicle's current trajectory, and the subsequent rectangular boxes are predicted / calculated discrete trajectories (only 3 are shown), where the width of the rectangular box represents the collision-sensitive width corresponding to the discrete trajectory. It can be seen that as the subsequent predicted discrete trajectories become less and less accurate, the collision-sensitive width becomes tighter (i.e., the collision-sensitive width of discrete trajectories with low trajectory confidence becomes tighter), and more attention is paid to the central area.

[0095] In an optional embodiment of the present invention, dividing the surrounding area of ​​the current position of the vehicle specifically includes the following steps:

[0096] The surrounding area of ​​the vehicle is divided into six division areas according to the horizontal line of the front bumper of the vehicle, the horizontal line of the rear axle, and the horizontal line of the rear bumper.

[0097] Specifically, Figure 3 As shown, FL represents the left front axle, FR represents the right front axle, RL represents the left rear axle, and RR represents the right rear axle, wherein six divided areas are shown.

[0098] After the six division areas are obtained, the target division area where the collision may occur is further determined in the division areas according to the driving direction of the vehicle (the vehicle is assumed to be an ordinary vehicle with front-wheel steering), as shown in the following table:

[0099] Driving Directions Target division area Go forward + straight Region 1 Previous + Turn Left Area 1+Area 2+Area 5 Forward + Turn Right Area 1+Area 6+Area 3 Back + Straight Region 4 Back + Turn Left Area 4 + Area 3 + Area 6 Back + Turn Right Area 4 + Area 5 + Area 2

[0100] In an optional embodiment of the present invention, setting an obstacle position coefficient for each target obstacle according to the distance between the target obstacle and the vehicle in the target division area specifically includes the following steps:

[0101] (1) If the distance between a first target obstacle among the target obstacles and the vehicle is not greater than a first preset distance, the obstacle position coefficient of the first target obstacle is set to 1;

[0102] (2) if the distance between the second target obstacle in the target obstacles and the vehicle is greater than the first preset distance and less than the second preset distance, the obstacle position coefficient of the second target obstacle is set according to a preset decreasing rule, wherein the preset decreasing rule is that when the distance is between the first preset distance and the second preset distance, the obstacle position coefficient is linearly decreased from 1 to 0 from near to far;

[0103] (3) If the distance between the third target obstacle among the target obstacles and the vehicle is greater than the second preset distance, the obstacle position coefficient of the third target obstacle is set to 0.

[0104] Specifically, according to the detection characteristics (effective detection range) of the sensor (ultrasonic + surround view camera), the obstacle position coefficient within the effective range and within the straight-line distance d1 around the vehicle is assigned a value of 1; the obstacle position coefficient between the straight-line distance d1 and d2 decreases linearly from 1 to 0 from near to far; the obstacle position coefficient of the obstacle that is more than d2 away from the vehicle is set to 0. Figure 4 shown.

[0105] In an optional embodiment of the present invention, a collision coefficient between each target obstacle and each discrete trajectory is calculated based on the collision sensitive width corresponding to each discrete trajectory, and a target collision coefficient corresponding to each target obstacle is determined according to the collision coefficient between each target obstacle and each discrete trajectory, specifically including the following steps:

[0106] (1) Calculate the collision coefficient between each target obstacle and each discrete trajectory according to the collision coefficient calculation formula Collision_Coe=CE / AE, where Collision_Coe represents the collision coefficient between a target obstacle and a discrete trajectory, CE represents the overlapping width between the target obstacle and the discrete trajectory, and AE represents half of the collision sensitive width corresponding to the discrete trajectory;

[0107] Specifically, as in the above example, the algorithm is executed once, and a total of 50 discrete trajectories are obtained. If the number of target obstacles determined is 10, then the collision coefficient between each target obstacle and each of the 50 discrete trajectories can be calculated. In this way, for each target obstacle, 50 collision coefficients are obtained, and each collision coefficient represents the collision coefficient between the target obstacle and the corresponding discrete trajectory. Figure 5 As shown, a schematic diagram of the calculation of the collision coefficient between a target obstacle and a discrete track is shown. Among them, the small rectangle represents the target obstacle, and the large rectangle represents the discrete track. According to the size and angle of the target obstacle, the size of the discrete track (the width is the collision sensitive width, and the length is the length of the vehicle), and the front angle, the overlapping width of the target obstacle and the discrete track can be calculated, and then the collision coefficient of the target obstacle and the discrete track can be calculated according to the above formula.

[0108] (2) The maximum collision coefficient among the collision coefficients between each target obstacle and each discrete trajectory is taken as the target collision coefficient corresponding to each target obstacle.

[0109] Specifically, as shown in the above content, for each target obstacle, 50 collision coefficients are obtained, and the maximum collision coefficient among them is used as the target collision coefficient corresponding to each target obstacle.

[0110] In an optional embodiment of the present invention, the risk coefficient of each target obstacle relative to the target discrete trajectory is calculated according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, which specifically includes the following steps:

[0111] The risk coefficient of each target obstacle relative to the target discrete trajectory is calculated according to the risk coefficient calculation formula: risk coefficient = obstacle position coefficient × target collision coefficient.

[0112] Specifically, the risk coefficient not only considers the target collision coefficient, but also the obstacle position coefficient of the target obstacle. The larger the obstacle position coefficient, the higher the accuracy of the detected target obstacle, and the corresponding risk coefficient should be larger. Therefore, performing the above product calculation can improve the accuracy of the risk coefficient.

[0113] In an optional embodiment of the present invention, determining whether each target obstacle has a collision risk with the target discrete trajectory based on the risk coefficient of each target obstacle with respect to the target discrete trajectory specifically includes the following steps:

[0114] If the risk factor is greater than the preset risk threshold, it is determined that the corresponding target obstacle has a collision risk with the target discrete trajectory.

[0115] In an optional embodiment of the present invention, the performance of the vehicle includes: the time required for the vehicle to complete braking, and determining the emergency braking timing according to the performance of the vehicle and the target discrete trajectory with collision risk specifically includes the following steps:

[0116] (1) Determine the time when the vehicle will collide in the future based on the target discrete trajectory with collision risk;

[0117] Specifically, as in the above example, if the target discrete trajectory with collision risk is the discrete trajectory at the fourth discrete time point, then it can be known that the time when the vehicle collides in the future is 400ms. Because there is a discrete trajectory every 100ms, the discrete trajectory at the fourth discrete time point corresponds to a time when the vehicle collides in the future of 400ms.

[0118] (2) Determine the timing of emergency braking based on the time required for the vehicle to complete braking and the time when the vehicle will collide in the future.

[0119] The method for determining low-speed emergency braking of the present invention includes the following improvements:

[0120] (1) Adding acceleration and deceleration and steering wheel speed to trajectory confidence can dynamically lock the effective trajectory, improve accuracy, and avoid "false braking";

[0121] (2) Introduce obstacle position coefficient. 1) Divide obstacles into regions and discard obstacles that have no effect on the vehicle's motion to reduce the amount of calculation; 2) The farther the obstacle is, the smaller the obstacle position coefficient is, which can be used to characterize the detection accuracy of the sensor (the farther the obstacle is, the less accurate it is);

[0122] (3) Traditional obstacle selection is a binary system. This invention expresses obstacle selection as a probabilistic model and expresses collision risk in numerical form (i.e., risk coefficient), which is more in line with natural laws.

[0123] Embodiment 2:

[0124] An embodiment of the present invention also provides a device for determining low-speed emergency braking, which is mainly used to execute the method for determining low-speed emergency braking provided in embodiment 1 of the present invention. The following is a specific introduction to the device for determining low-speed emergency braking provided in the embodiment of the present invention.

[0125] Figure 6 is a schematic diagram of a device for determining low-speed emergency braking according to an embodiment of the present invention, such as Figure 6 As shown, the device mainly includes: a first calculation unit 10, a division and determination unit 20, a setting unit 30, a calculation and determination unit 40, a second calculation unit 50, a first determination unit 60 and a second determination unit 70, wherein:

[0126] A first calculation unit is used to calculate the discrete trajectories of the vehicle at each discrete time point in a preset future time and the trajectory confidence corresponding to each discrete trajectory according to the current state information of the vehicle, and calculate the collision sensitive width corresponding to each discrete trajectory according to the trajectory confidence and the width of the vehicle, wherein the time intervals between adjacent discrete time points are the same;

[0127] A division and determination unit, used to divide the surrounding area of ​​the current position of the vehicle, and determine a target division area where a collision may occur in the division areas obtained according to the driving direction of the vehicle;

[0128] A setting unit, used to set an obstacle position coefficient for each target obstacle according to the distance between the target obstacle and the vehicle in the target division area, so as to obtain an obstacle position coefficient for each target obstacle;

[0129] A calculation and determination unit, configured to calculate a collision coefficient between each target obstacle and each discrete track based on a collision-sensitive width corresponding to each discrete track, and determine a target collision coefficient corresponding to each target obstacle according to the collision coefficient between each target obstacle and each discrete track;

[0130] A second calculation unit is used to calculate a risk coefficient of each target obstacle relative to a target discrete trajectory according to an obstacle position coefficient of each target obstacle and a target collision coefficient corresponding thereto, wherein the target discrete trajectory is a discrete trajectory corresponding to the target collision coefficient;

[0131] A first determination unit is used to determine whether each target obstacle has a collision risk with the target discrete trajectory based on a risk coefficient of each target obstacle relative to the target discrete trajectory;

[0132] The second determination unit is configured to determine an emergency braking timing according to the performance of the vehicle and a target discrete trajectory with a collision risk if there is a collision risk.

[0133] In an embodiment of the present invention, a low-speed emergency braking determination device is provided, comprising: calculating discrete trajectories of the vehicle at each discrete time point in a preset future time and trajectory confidences corresponding to each discrete trajectory based on current state information of the vehicle, and calculating collision-sensitive widths corresponding to each discrete trajectory based on each trajectory confidence and the width of the vehicle, wherein the time intervals between adjacent discrete time points are the same; dividing the surrounding area of ​​the current position of the vehicle, and determining a target divided area where a collision may occur in the divided areas obtained according to the driving direction of the vehicle; setting an obstacle position coefficient for each target obstacle in the target divided area according to the distance between the target obstacle and the vehicle, and obtaining an obstacle coefficient for each target obstacle. position coefficient; calculating the collision coefficient of each target obstacle with each discrete trajectory based on the collision sensitive width corresponding to each discrete trajectory, and determining the target collision coefficient corresponding to each target obstacle according to the collision coefficient of each target obstacle with each discrete trajectory; calculating the risk coefficient of each target obstacle relative to the target discrete trajectory according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, wherein the target discrete trajectory is the discrete trajectory corresponding to the target collision coefficient; determining whether each target obstacle has a collision risk with the target discrete trajectory based on the risk coefficient of each target obstacle relative to the target discrete trajectory; if there is a collision risk, determining the emergency braking timing according to the performance of the vehicle and the target discrete trajectory with the collision risk. It can be seen from the above description that in the low-speed emergency braking determination device of the present invention, the credibility of each discrete trajectory is characterized by the trajectory confidence, and the collision sensitive width corresponding to each discrete trajectory is calculated based on the trajectory confidence, so that the collision sensitive width of the discrete trajectory with low trajectory confidence can be tightened, thereby paying more attention to the central area, improving accuracy, and avoiding "false braking". In addition, the surrounding area of ​​the current position of the vehicle is divided into regions, and the target divided area where the collision may occur is determined from the divided divided areas, and the calculation of obstacles in the divided areas that have no effect on the movement of the vehicle is abandoned, reducing the subsequent calculation amount, and setting an obstacle position coefficient for the target obstacle in the target divided area to characterize the detection accuracy of the sensor. Finally, the target collision coefficient corresponding to each target obstacle is calculated based on the collision sensitive width corresponding to each discrete trajectory, and the risk coefficient of each target obstacle relative to the target discrete trajectory is calculated according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, and whether there is a collision risk is determined based on the risk coefficient. The above collision risk determination process is more in line with natural laws, so that the final determined emergency braking timing is more accurate, alleviating the technical problem of poor accuracy of the existing low-speed emergency braking.

[0134] Optionally, the first calculation unit is further used to: calculate the formula HeadAng according to the vehicle head angle [i] =HeadAng [i-1]+YawRate*T calculates the head angle of the vehicle at each discrete time point in the future preset time, where HeadAng [i] HeadAng represents the vehicle's head angle at the i-th discrete time point in the future preset time. [i-1] It represents the head angle of the vehicle at the (i-1)th discrete time point in the future preset time, YawRate represents the angular velocity in the current state information, T represents the time interval, and when i is 1, HeadAng [i-1] Indicates the current vehicle head angle in the current state information; calculates the formula X according to the vehicle's X coordinate [i] =X [i-1] +V [i] *cos(HeadAng [i]) *T calculates the x coordinates of the vehicle at each discrete time point in the future preset time, where X [i] represents the X coordinate of the vehicle at the i-th discrete time point in the future preset time, X [i-1] represents the x-coordinate of the vehicle at the (i-1)th discrete time point in the future preset time, V [i] HeadAng represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i] represents the vehicle's front angle at the i-th discrete time point in the future preset time, T represents the time interval, when i is 1, X [i-1] Indicates the current x coordinate of the vehicle in the current state information; calculates the formula Y based on the vehicle's Y coordinate [i] =Y [i-1] +V [i] *sin(HeadAng [i] )*T calculates the Y coordinate of the vehicle at each discrete time point in the future preset time, where Y [i] represents the Y coordinate of the vehicle at the i-th discrete time point in the future preset time, Y [i-1] represents the Y coordinate of the vehicle at the (i-1)th discrete time point in the future preset time, V [i] HeadAng represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i] represents the vehicle's front angle at the i-th discrete time point in the future preset time, T represents the time interval, when i is 1, Y [i-1] Represents the current Y coordinate of the vehicle in the current state information; the vehicle head angle at each discrete time point in the future preset time, the vehicle X coordinate at each discrete time point in the future preset time, and the vehicle Y coordinate at each discrete time point in the future preset time are used as the discrete trajectory of the vehicle at each discrete time point in the future preset time; according to the trajectory confidence calculation formula Confidence [i]=A1*(Distance Pred -Distance [i] ) / Distance Pred +A2*(Lgt AccMax -Lgt Acc ) / Lgt AccMax +A3*(Steer SpdMax -Steer Spd ) / Steer SpdMax

[0135] Calculate the trajectory confidence corresponding to each discrete trajectory, where Confidence [i] Represents the trajectory confidence of the discrete trajectory at the i-th discrete time point, Distance Pred Indicates the total length of the discrete trajectory corresponding to the current state information, Distance [i] represents the length of the discrete trajectory at the ith discrete time point, Lgt AccMax Indicates the maximum longitudinal acceleration, Lgt Acc Indicates the longitudinal acceleration in the current state information, Steer SpdMax Indicates the maximum rotation speed of the steering wheel, Steer Spd It represents the steering wheel rotation speed in the current state information, and A1, A2, and A3 represent the preset weight coefficients. The collision sensitive width corresponding to each discrete trajectory is calculated according to the collision sensitive width calculation formula: collision sensitive width = vehicle width × trajectory confidence.

[0136] Optionally, the dividing and determining unit is further used to: divide the surrounding area of ​​the vehicle into six divided areas according to the horizontal line of the front bumper, the horizontal line of the rear axle and the horizontal line of the rear bumper of the vehicle;

[0137] The setting unit is further used for: if the distance between a first target obstacle among the target obstacles and the vehicle is not greater than a first preset distance, setting the obstacle position coefficient of the first target obstacle to 1; if the distance between a second target obstacle among the target obstacles and the vehicle is greater than the first preset distance and less than the second preset distance, setting the obstacle position coefficient of the second target obstacle according to a preset decreasing rule, wherein the preset decreasing rule is that when the distance is between the first preset distance and the second preset distance, the obstacle position coefficient is linearly decreased from 1 to 0 from near to far; if the distance between a third target obstacle among the target obstacles and the vehicle is greater than the second preset distance, setting the obstacle position coefficient of the third target obstacle to 0.

[0138] Optionally, the calculation and determination unit is also used to: calculate the collision coefficient between each target obstacle and each discrete trajectory according to the collision coefficient calculation formula Collision_Coe=CE / AE, wherein Collision_Coe represents the collision coefficient between a target obstacle and a discrete trajectory, CE represents the overlapping width between the target obstacle and the discrete trajectory, and AE represents half of the collision sensitive width corresponding to the discrete trajectory; and use the maximum collision coefficient among the collision coefficients between each target obstacle and each discrete trajectory as the target collision coefficient corresponding to each target obstacle.

[0139] Optionally, the second calculation unit is further used to calculate the risk coefficient of each target obstacle relative to the target discrete trajectory according to the risk coefficient calculation formula: risk coefficient = obstacle position coefficient × target collision coefficient.

[0140] Optionally, the first determination unit is further configured to: if the risk coefficient is greater than a preset risk threshold, determine that the corresponding target obstacle has a collision risk with the target discrete trajectory.

[0141] Optionally, the vehicle's performance includes: the time required for the vehicle to complete braking, and the second determination unit is further used to: determine the time when the vehicle will collide in the future based on the target discrete trajectory with collision risk; determine the timing of emergency braking based on the time required for the vehicle to complete braking and the time when the vehicle will collide in the future.

[0142] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0143] like Figure 7 As shown, an electronic device 600 provided in an embodiment of the present application includes: a processor 601, a memory 602 and a bus, wherein the memory 602 stores machine-readable instructions executable by the processor 601. When the electronic device is running, the processor 601 communicates with the memory 602 through the bus, and the processor 601 executes the machine-readable instructions to perform the steps of the method for determining low-speed emergency braking as described above.

[0144] Specifically, the memory 602 and the processor 601 can be general-purpose memories and processors, which are not specifically limited here. When the processor 601 runs the computer program stored in the memory 602, the method for determining low-speed emergency braking can be executed.

[0145] The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 601. The above processor 601 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 602, and the processor 601 reads the information in the memory 602 and completes the steps of the above method in combination with its hardware.

[0146] Corresponding to the above-mentioned method for determining low-speed emergency braking, an embodiment of the present application also provides a computer-readable storage medium, which stores machine-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned method for determining low-speed emergency braking.

[0147] The low-speed emergency braking determination device provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0148] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0149] For another example, the flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0150] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0152] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method for determining low-speed emergency braking described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0153] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0154] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solution of the present application, rather than to limit it. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solution recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiment of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for determining low-speed emergency braking, characterized in that: include: Calculating, according to the current state information of the vehicle, discrete trajectories of the vehicle at each discrete time point within a preset future time and trajectory confidences corresponding to each discrete trajectory, and calculating, according to each trajectory confidence and the width of the vehicle, a collision-sensitive width corresponding to each discrete trajectory, wherein the time intervals between adjacent discrete time points are the same; Dividing the surrounding area of ​​the current position of the vehicle, and determining a target divided area where a collision may occur in the divided areas according to the driving direction of the vehicle; Setting an obstacle position coefficient for each target obstacle in the target divided area according to the distance between the target obstacle and the vehicle to obtain an obstacle position coefficient for each target obstacle; Calculating a collision coefficient between each of the target obstacles and each of the discrete trajectories based on a collision-sensitive width corresponding to each of the discrete trajectories, and determining a target collision coefficient corresponding to each of the target obstacles according to the collision coefficient between each of the target obstacles and each of the discrete trajectories; Calculating a risk coefficient of each target obstacle relative to a target discrete trajectory according to an obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, wherein the target discrete trajectory is a discrete trajectory corresponding to the target collision coefficient; Determining whether each of the target obstacles has a collision risk with the target discrete trajectory based on a risk coefficient of each of the target obstacles with respect to the target discrete trajectory; If there is a collision risk, an emergency braking timing is determined according to the performance of the vehicle and a target discrete trajectory with a collision risk.

2. The method according to claim 1, characterized in that: Calculating the discrete trajectories of the vehicle at each discrete time point within a preset future time and the trajectory confidence corresponding to each discrete trajectory according to the current state information of the vehicle, including: Calculate the formula HeadAng based on the vehicle head angle [i] =HeadAng [i-1] +YawRate*T calculates the head angle of the vehicle at each discrete time point in the future preset time, where HeadAng [i] HeadAng represents the head angle of the vehicle at the i-th discrete time point in the future preset time. [i-1] represents the head angle of the vehicle at the (i-1)th discrete time point in the future preset time, YawRate represents the angular velocity in the current state information, T represents the time interval, when i is 1, HeadAng [i-1] Indicates the current vehicle head angle in the current state information; X [i] =X [i-1] +V [i] *cos(HeadAng [i] )*T calculates the x coordinates of the vehicle at each discrete time point in the future preset time, where X [i] represents the x-coordinate of the vehicle at the i-th discrete time point in the future preset time, X [i-1] represents the X coordinate of the vehicle at the (i-1)th discrete time point in the future preset time, V [i] HeadAng represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i] represents the front angle of the vehicle at the i-th discrete time point in the future preset time, T represents the time interval, when i is 1, X [i-1] represents the current X coordinate of the vehicle in the current state information; Calculate the formula Y based on the vehicle's Y coordinate [i] =Y [i-1] +V [i] *sin(HeadAng [i] )*T calculates the Y coordinate of the vehicle at each discrete time point in the future preset time, where Y [i] represents the Y coordinate of the vehicle at the i-th discrete time point in the future preset time, Y [i-1] represents the Y coordinate of the vehicle at the (i-1)th discrete time point in the future preset time, V [i] HeadAng represents the speed of the vehicle at the i-th discrete time point in the future preset time. [i] represents the front angle of the vehicle at the i-th discrete time point in the future preset time, T represents the time interval, when i is 1, Y [i-1] represents the current Y coordinate of the vehicle in the current state information; The front angle of the vehicle at each discrete time point in the future preset time, the X coordinate of the vehicle at each discrete time point in the future preset time, and the Y coordinate of the vehicle at each discrete time point in the future preset time are used as discrete trajectories of the vehicle at each discrete time point in the future preset time; According to the trajectory confidence calculation formula Confidence [i] =A1*(Distance Pred -Distance [i] ) / Distance Pred +A2*(Lgt AccMax -Lgt Acc ) / Lgt AccMax +A3*(Steer Spdax -Steer Spd ) / Steer SpdMax Calculate the trajectory confidence corresponding to each discrete trajectory, where Confidence [i] Represents the trajectory confidence of the discrete trajectory at the i-th discrete time point, Distance Pred Indicates the total length of the discrete trajectory corresponding to the current state information, Distance [i] represents the length of the discrete trajectory at the ith discrete time point, Lgt AccMax Indicates the maximum longitudinal acceleration, Lgt Acc Indicates the longitudinal acceleration in the current state information, Steer SpdMax Indicates the maximum rotation speed of the steering wheel, Steer Spd represents the rotation speed of the steering wheel in the current state information, and A1, A2, and A3 represent preset weight coefficients; Calculating the collision sensitive width corresponding to each discrete trajectory according to the trajectory confidence and the width of the vehicle, including: The collision-sensitive width corresponding to each discrete trajectory is calculated according to the collision-sensitive width calculation formula: collision-sensitive width=vehicle width×trajectory confidence.

3. The method according to claim 1, characterized in that The surrounding area of ​​the current position of the vehicle is divided, including: Dividing the surrounding area of ​​the vehicle into six divided areas according to a horizontal line of a front bumper, a horizontal line of a rear axle, and a horizontal line of a rear bumper of the vehicle; Setting an obstacle position coefficient for each target obstacle in the target divided area according to the distance between the target obstacle and the vehicle includes: If the distance between a first target obstacle among the target obstacles and the vehicle is not greater than a first preset distance, setting an obstacle position coefficient of the first target obstacle to 1; If the distance between a second target obstacle among the target obstacles and the vehicle is greater than the first preset distance and less than the second preset distance, the obstacle position coefficient of the second target obstacle is set according to a preset decreasing rule, wherein the preset decreasing rule is that when the distance is between the first preset distance and the second preset distance, the obstacle position coefficient is linearly decreased from 1 to 0 from near to far; If the distance between a third target obstacle among the target obstacles and the vehicle is greater than the second preset distance, the obstacle position coefficient of the third target obstacle is set to 0.

4. The method according to claim 1, characterized in that Calculating a collision coefficient between each of the target obstacles and each of the discrete trajectories based on a collision-sensitive width corresponding to each of the discrete trajectories, and determining a target collision coefficient corresponding to each of the target obstacles according to the collision coefficient between each of the target obstacles and each of the discrete trajectories, including: The collision coefficient between each target obstacle and each discrete track is calculated according to the collision coefficient calculation formula Collision_Coe=CE / AE, wherein Collision_Coe represents the collision coefficient between one target obstacle and one discrete track, CE represents the overlapping width between the target obstacle and the discrete track, and AE represents half of the collision sensitive width corresponding to the discrete track; The maximum collision coefficient among the collision coefficients between each target obstacle and each discrete trajectory is used as the target collision coefficient corresponding to each target obstacle.

5. The method according to claim 1, characterized in that Calculating the risk coefficient of each target obstacle relative to the target discrete trajectory according to the obstacle position coefficient of each target obstacle and its corresponding target collision coefficient, including: The risk coefficient of each target obstacle relative to the target discrete trajectory is calculated according to the risk coefficient calculation formula: risk coefficient = obstacle position coefficient × target collision coefficient.

6. The method according to claim 1, characterized in that Determining whether each target obstacle has a collision risk with the target discrete trajectory based on a risk coefficient of each target obstacle with respect to the target discrete trajectory includes: If the risk coefficient is greater than a preset risk threshold, it is determined that the corresponding target obstacle has a collision risk with the target discrete trajectory.

7. The method according to claim 1, characterized in that The performance of the vehicle includes: the time required for the vehicle to complete braking. The emergency braking timing is determined according to the performance of the vehicle and the target discrete trajectory with collision risk, including: Determining a time when the vehicle will collide in the future based on the target discrete trajectory with collision risk; The emergency braking timing is determined according to the time required for the vehicle to complete braking and the time when the vehicle will collide in the future.

8. A low-speed emergency braking determination device, characterized in that: include: a first calculation unit, configured to calculate, according to current state information of the vehicle, discrete trajectories of the vehicle at discrete time points within a preset future time and trajectory confidences corresponding to the discrete trajectories, and to calculate, according to the trajectory confidences and the width of the vehicle, a collision-sensitive width corresponding to the discrete trajectories, wherein time intervals between adjacent discrete time points are the same; a dividing and determining unit, configured to divide the surrounding area of ​​the current position of the vehicle, and determine a target divided area where a collision may occur in the divided areas according to the driving direction of the vehicle; a setting unit, configured to set an obstacle position coefficient for each target obstacle according to the distance between the target obstacle and the vehicle in the target divided area, so as to obtain an obstacle position coefficient for each target obstacle; a calculation and determination unit, configured to calculate a collision coefficient between each of the target obstacles and each of the discrete trajectories based on a collision-sensitive width corresponding to each of the discrete trajectories, and determine a target collision coefficient corresponding to each of the target obstacles according to the collision coefficient between each of the target obstacles and each of the discrete trajectories; A second calculation unit is used to calculate a risk coefficient of each target obstacle relative to a target discrete trajectory according to an obstacle position coefficient of each target obstacle and a target collision coefficient corresponding thereto, wherein the target discrete trajectory is a discrete trajectory corresponding to the target collision coefficient; A first determination unit is used to determine whether each of the target obstacles has a collision risk with the target discrete trajectory based on a risk coefficient of each of the target obstacles with respect to the target discrete trajectory; The second determination unit is configured to determine an emergency braking timing according to the performance of the vehicle and a target discrete trajectory with a collision risk if there is a collision risk.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores machine-executable instructions. When the machine-executable instructions are called and executed by a processor, the machine-executable instructions prompt the processor to execute the method according to any one of claims 1 to 7.

Images