Vehicle collision avoidance method, device and equipment

Abstract

The invention relates to the technical field of vehicle collision avoidance, and discloses a vehicle collision avoidance method, device and equipment, and the method comprises the steps: when a vehicle turns, preliminarily determining whether a target two-wheeled vehicle is on a driving track of the vehicle according to the predicted position information of the vehicle and the target two-wheeled vehicle at the first collision time and the second collision time, and if yes, determining that the target two-wheeled vehicle is on the driving track of the vehicle; if so, taking the two-wheeled vehicle as a preliminary risk target; determining an important risk target according to the first collision time and the second collision time of the initial risk target, the relative distance between the vehicle and the initial risk target, and the relationship between the initial risk target and the driving track of the vehicle when the initial risk target takes the collision avoidance action; and when the vehicle decelerates to avoid collision, determining a target deceleration according to a preset deceleration calculation rule, and determining whether to trigger automatic emergency braking according to the relationship between the target deceleration and the preset deceleration. According to the application, under the condition that one camera is arranged, whether the automatic emergency brake is triggered or not can be accurately judged.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle collision avoidance, and in particular to a vehicle collision avoidance method, device and equipment. Background Art

[0002] With the increase in the number of vehicles, the risk of traffic accidents is also increasing. Since the driver often fails to pay attention to the oncoming two-wheeled vehicles or pedestrians during the turning process, traffic accidents may occur, resulting in personal or property losses. Therefore, the automobile safety C-NCAP 2024 regulations also stipulate that vehicles often encounter oncoming two-wheeled vehicles during turning. At present, when the vehicle is turning, emergency braking is performed when encountering a two-wheeled vehicle. Usually, visual perception and corner radar are used to make the judgment, multi-visual perception is used to make the judgment, or multiple radars are used. These three methods of the existing technology require the installation of multiple cameras and radars on the vehicle, which increases the cost, and the amount of calculation is large when judging whether to perform emergency braking. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a vehicle collision avoidance method, device and equipment, which can accurately determine whether to trigger automatic emergency braking by setting up a camera.

[0004] In a first aspect, an embodiment of the present application provides a vehicle collision avoidance method, comprising:

[0005] When the self-vehicle turns, the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time is calculated according to a preset calculation rule, and whether the target two-wheeled vehicle is on the driving track of the self-vehicle is preliminarily determined according to the predicted position information, and the target two-wheeled vehicle preliminarily determined to be on the driving track of the self-vehicle is used as a preliminary risk target; wherein, the first collision time is the collision time between the front of the self-vehicle and the target two-wheeled vehicle, and the second collision time is the collision time between the rear of the self-vehicle and the target two-wheeled vehicle;

[0006] Determine an important risk target according to the first collision time of the preliminary risk target, the second collision time, the relative distance between the ego vehicle and the preliminary risk target, and the relationship between the preliminary risk target and the driving trajectory of the ego vehicle when taking a collision avoidance action;

[0007] When the self-vehicle decelerates to avoid collision with the important risk target, a target deceleration is determined according to a preset deceleration calculation rule, and whether to trigger automatic emergency braking is determined according to a relationship between the target deceleration and the preset deceleration.

[0008] In some embodiments, the predicted position information includes: a predicted first lateral position of the front of the target two-wheeled vehicle at the first collision time, a predicted second lateral position of the rear of the target two-wheeled vehicle at the second collision time, a predicted third lateral position of the front of the own vehicle at the first collision time, and a predicted fourth lateral position of the rear of the own vehicle at the second collision time.

[0009] In some embodiments, the step of calculating the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time according to a preset calculation rule, and preliminarily determining whether the target two-wheeled vehicle is on the driving track of the self-vehicle according to the predicted position information, further includes:

[0010] Obtaining the first collision time according to the longitudinal distance between the front of the own vehicle and the center point of the target two-wheeled vehicle, the current longitudinal speed of the own vehicle and the current longitudinal speed of the target two-wheeled vehicle;

[0011] The second collision time is obtained according to the longitudinal distance between the front end of the own vehicle and the center point of the target two-wheeled vehicle, the current longitudinal speed of the own vehicle, the current longitudinal speed of the target two-wheeled vehicle, the length of the own vehicle and the length coefficient of the own vehicle.

[0012] In some embodiments, the step of calculating the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time according to a preset calculation rule, and preliminarily determining whether the target two-wheeled vehicle is on the driving track of the self-vehicle according to the predicted position information, includes:

[0013] Acquire the first lateral position according to the current lateral position of the target two-wheeled vehicle, the current lateral speed of the target two-wheeled vehicle, the first collision time, and the current lateral acceleration of the target two-wheeled vehicle;

[0014] acquiring the second lateral position according to the current lateral position of the target two-wheeled vehicle, the current lateral speed of the target two-wheeled vehicle, the second collision time and the current lateral acceleration of the target two-wheeled vehicle;

[0015] Acquire the third lateral position and the fourth lateral position according to a third-order Bezier curve;

[0016] It is preliminarily determined whether the target two-wheeled vehicle is on the driving track of the own vehicle based on the first lateral position, the second lateral position, the third lateral position, the fourth lateral position, the own vehicle width and the target two-wheeled vehicle width.

[0017] In some embodiments, the preliminarily determining whether the target two-wheeled vehicle is on the driving track of the own vehicle based on the first lateral position, the second lateral position, the third lateral position, the fourth lateral position, the own vehicle width and the target two-wheeled vehicle width includes:

[0018] Predicting a first relative lateral distance between the front of the target two-wheeled vehicle and the front of the own vehicle based on the first lateral position, the third lateral position, the own vehicle width, and the target two-wheeled vehicle width;

[0019] predicting a second relative lateral distance between the rear end of the target two-wheeled vehicle and the rear end of the own vehicle based on the second lateral position, the fourth lateral position, the own vehicle width, and the target two-wheeled vehicle width;

[0020] If any one of the first relative lateral distance and the second relative lateral distance is less than zero, it is preliminarily determined whether the target two-wheeled vehicle is on the driving track of the own vehicle.

[0021] In some embodiments, determining the important risk target according to the first collision time of the preliminary risk target, the second collision time, the relative distance between the ego vehicle and the preliminary risk target, and the relationship between the preliminary risk target and the driving trajectory of the ego vehicle when taking a collision avoidance action includes:

[0022] Determining whether the first collision time and the second collision time are within a preset collision time range;

[0023] If yes, determining whether the first relative distance between the front of the vehicle and the preliminary risk target and the second relative distance between the rear of the vehicle and the preliminary risk target are within a preset relative distance range;

[0024] If so, when the preliminary risk target takes a collision avoidance action, further determining whether the preliminary risk target is on the driving track of the vehicle according to a preset calculation rule corresponding to the collision avoidance action;

[0025] If yes, then determine the relative coordinates of the preliminary risk target according to the relative position coordinate relationship of the preliminary risk target with respect to the ego vehicle, and judge whether the lateral coordinates of each judgment point of each preliminary risk target are on the driving track of the ego vehicle according to the relative coordinates, the driving curvature of the ego vehicle and the curvature radius;

[0026] If any of the judgment points of the preliminary risk targets is on the driving trajectory of the vehicle, the current preliminary risk target is taken as an important risk target.

[0027] In some embodiments, when the preliminary risk target takes a collision avoidance action, further determining whether the preliminary risk target is on the driving trajectory of the vehicle according to a preset calculation rule corresponding to the collision avoidance action includes:

[0028] If the preliminary risk target decelerates, combining the calibrated deceleration of the preliminary risk target with the preset calculation rule to determine whether the preliminary risk target is currently on the driving trajectory of the vehicle;

[0029] If the preliminary risk target turns, determine a first heading angle of the preliminary risk target according to the angle between the preliminary risk target and the vehicle, the curvature of the preliminary risk target, and the longitudinal distance between the preliminary risk target and the vehicle;

[0030] Determining the longitudinal speed of the current preliminary risk target and the lateral speed of the current preliminary risk target according to the speed of the current preliminary risk target and the first heading angle;

[0031] According to the first heading angle of the current preliminary risk target, the lateral speed of the current preliminary risk target and the longitudinal speed of the current preliminary risk target in combination with a preset calculation rule, it is determined whether the current preliminary risk target is on the driving trajectory of the vehicle.

[0032] In some embodiments, determining the relative coordinates of the preliminary risk target according to the relative position coordinate relationship of the preliminary risk target with respect to the ego vehicle, and judging whether the lateral coordinates of each judgment point of each preliminary risk target is on the driving track of the ego vehicle according to the relative coordinates, the driving curvature of the ego vehicle and the curvature radius, includes:

[0033] Calculate the relative position coordinates of the judgment point of the preliminary risk target relative to the coordinate origin through coordinate transformation;

[0034] Obtaining the lateral coordinates of each of the judgment points of each of the preliminary risk targets according to the relative position coordinates of the judgment point of the preliminary risk target relative to the coordinate origin, the travel curvature of the vehicle and the curvature radius;

[0035] If the lateral coordinate of the judgment point is less than 0, it is determined that the current judgment point is on the driving track of the vehicle.

[0036] In a second aspect, an embodiment of the present application provides a vehicle collision avoidance device, comprising:

[0037] A preliminary risk target determination module is used to calculate the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time according to a preset calculation rule when the self-vehicle turns, and preliminarily determine whether the target two-wheeled vehicle is on the driving track of the self-vehicle according to the predicted position information, and take the target two-wheeled vehicle preliminarily determined to be on the driving track of the self-vehicle as the preliminary risk target; wherein the first collision time is the collision time between the front of the self-vehicle and the target two-wheeled vehicle, and the second collision time is the collision time between the rear of the self-vehicle and the target two-wheeled vehicle;

[0038] an important risk target determination module, configured to determine an important risk target according to the first collision time of the preliminary risk target, the second collision time, the relative distance between the ego vehicle and the preliminary risk target, and the relationship between the preliminary risk target and the driving trajectory of the ego vehicle when taking a collision avoidance action;

[0039] The automatic emergency brake triggering module is used to determine the target deceleration according to the preset deceleration calculation rule when the self-vehicle decelerates to avoid collision with the important risk target, and determine whether to trigger the automatic emergency brake according to the relationship between the target deceleration and the preset deceleration.

[0040] In a third aspect, an embodiment of the present application provides a terminal device, which includes a processor and a memory, wherein the memory stores a computer program, and the processor is used to execute the computer program to implement the above-mentioned vehicle collision avoidance method.

[0041] The embodiments of the present application have the following beneficial effects: when the vehicle turns, in order to avoid colliding with the target two-wheeled vehicle traveling in the opposite direction of the adjacent lane, the embodiments of the present application first determine the preliminary risk target from the target two-wheeled vehicles, and further determine the important risk target in the preliminary risk target; after determining the important risk target, and when the vehicle does not take any collision avoidance action, the embodiments of the present application calculate how much deceleration the vehicle needs to avoid the collision under the current situation. If the required target deceleration reaches the preset deceleration, it means that if the vehicle adopts the collision avoidance method of deceleration, it is not feasible, and the AEB needs to be directly triggered to stop the vehicle in time to avoid colliding with the two-wheeled vehicle in the opposite adjacent lane. The embodiments of the present application determine the two-wheeled vehicles with a greater collision risk step by step in this way, thereby avoiding the problem of large amount of calculation caused by the need to calculate whether the target two-wheeled vehicles traveling in the opposite direction of the adjacent lane need to be triggered AEB, and by judging whether the important risk target triggers AEB, the automatic emergency braking judgment is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 A schematic diagram showing a working condition in which a two-wheeled vehicle is traveling in an adjacent opposite lane when the vehicle of the embodiment of the present application is turning;

[0044] Figure 2 A first flow chart of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0045] Figure 3 A second flow chart of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0046] Figure 4 A third flow chart of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0047] Figure 5 A schematic diagram showing the camera installation position of an embodiment of the present application is shown;

[0048] Figure 6 A fourth process diagram of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0049] Figure 7 A schematic diagram of a third-order Bezier curve in an embodiment of the present application is shown;

[0050] Figure 8 A fifth process diagram of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0051] Fig. 9 A sixth flow chart of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0052] Fig.10 A schematic diagram of a scenario of an embodiment of the present application is shown;

[0053] Fig.11 A seventh flow chart of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0054] Fig.12 A schematic diagram of acceleration of an embodiment of the present application is shown;

[0055] Fig.13 A structural schematic diagram of a vehicle collision avoidance device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0057] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0058] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are intended only to indicate specific features, numbers, steps, operations, elements, components or a combination of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or a combination of the foregoing items or increasing the possibility of one or more features, numbers, steps, operations, elements, components or a combination of the foregoing items. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions and cannot be understood as indicating or implying relative importance.

[0059] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0060] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0061] The vehicle collision avoidance method proposed in this embodiment is mainly aimed at Figure 1 The illustrated working condition is that when the vehicle is turning (left or right), there is a two-wheeled vehicle driving in the adjacent opposite lane.

[0062] The vehicle collision avoidance method is described below in conjunction with some specific embodiments.

[0063] Figure 2 A schematic flow chart of a vehicle collision avoidance method according to an embodiment of the present application is shown. Exemplarily, the vehicle collision avoidance method comprises the following steps:

[0064] Step S100, when the self-vehicle turns, the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time is calculated according to the preset calculation rules, and it is preliminarily determined whether the target two-wheeled vehicle is on the driving trajectory of the self-vehicle based on the predicted position information, and the target two-wheeled vehicle preliminarily determined to be on the driving trajectory of the self-vehicle is used as a preliminary risk target.

[0065] Before step S100, in order to determine whether the two-wheeled vehicle traveling in the opposite direction of the adjacent lane on the left side of the vehicle is the target two-wheeled vehicle or the two-wheeled vehicle traveling in the opposite direction of the adjacent lane on the right side of the vehicle is the target two-wheeled vehicle, it is first necessary to determine whether the vehicle is turning. The following method can be used to determine whether the vehicle is turning.

[0066] Combination Figure 3 and Figure 4 The following describes the judgment of whether the vehicle is turning. During the driving process of the vehicle, step 10 is used to judge whether the vehicle uses the turn signal correctly. Figure 4 The illustrated step 10 specifically includes: step S11, determining whether the turn signal is on. According to step S11, if the left turn signal is on, step 12 is executed to determine whether the steering wheel turns left at an angle greater than 0 degrees. If the steering wheel turns left at an angle greater than 0 degrees, step S13 is executed to turn the turn signal correctly. If it is determined in step S12 that the steering wheel turns left at an angle less than or equal to 0 degrees, step S14 is executed to incorrectly use the turn signal. According to step S11, if the right turn signal is on, step 15 is executed to determine whether the steering wheel turns right at an angle greater than 0 degrees. If the steering wheel turns right at an angle greater than 0 degrees, step S16 is executed to turn the turn signal correctly. If it is determined in step S15 that the steering wheel turns right at an angle less than or equal to 0 degrees, step S14 is executed to incorrectly use the turn signal.

[0067] In step S10, if it is determined that the vehicle uses the turn signal correctly, step S20 is executed to directly determine the risk target according to the direction of the turn signal. That is, if the turn signal is used correctly, if the turn signal is turned to the left, the two-wheeled vehicle traveling in the opposite direction of the adjacent lane on the left side of the vehicle is a two-wheeled vehicle that may have a collision risk, and the two-wheeled vehicle traveling in the opposite direction of the adjacent lane on the left side of the vehicle is taken as the target two-wheeled vehicle; if the turn signal is turned to the right, the two-wheeled vehicle traveling in the opposite direction of the adjacent lane on the right side of the vehicle is a two-wheeled vehicle that may have a collision risk, and the two-wheeled vehicle traveling in the opposite direction of the adjacent lane on the right side of the vehicle is taken as the target two-wheeled vehicle. If it is determined in step S10 that the vehicle does not use the turn signal correctly, that is, the steering wheel of the vehicle is turned, but the vehicle is not turned on or turned incorrectly, the steering of the vehicle is determined according to the vehicle speed and the steering angle of the steering wheel of the vehicle. Step S30, the steering of the steering wheel of the vehicle is determined. If it is determined in step S30 that the steering wheel of the vehicle turns left, step S40 is executed to determine whether the steering angle of the steering wheel of the vehicle turns left is greater than the preset threshold value at the corresponding speed by looking up the table. If it is determined in step S40 that the turning angle of the steering wheel of the self-vehicle turning left is greater than or equal to the preset threshold value at the corresponding speed, step S50 is executed to take the two-wheeled vehicle traveling in the opposite direction of the adjacent lane on the left side of the self-vehicle as the target two-wheeled vehicle. If it is determined in step S40 that the turning angle of the steering wheel of the self-vehicle turning left is less than the preset threshold value at the corresponding speed, step S60 is executed to determine that the self-vehicle has not turned. If it is determined in step S30 that the steering wheel of the self-vehicle turns right, step S70 is executed to determine whether the turning angle of the steering wheel of the self-vehicle turning right is greater than the preset threshold value at the corresponding speed by looking up the table. If it is determined in step S70 that the turning angle of the steering wheel of the self-vehicle turning right is greater than or equal to the preset threshold value at the corresponding speed, step S80 is executed to take the two-wheeled vehicle traveling in the opposite direction of the adjacent lane on the right side of the self-vehicle as the target two-wheeled vehicle. If it is determined in step S80 that the turning angle of the steering wheel of the self-vehicle turning right is less than the preset threshold value at the corresponding speed, step S60 is executed to determine that the self-vehicle has not turned.

[0068] Exemplarily, the table searched in step S40 and step S70 is shown in Table 1:

[0069] Table 1:

[0070]

[0071]

[0072] If it is determined that the vehicle is turning and the direction of the turn is determined, target two-wheeled vehicles with collision risks can also be determined. However, not all of these target two-wheeled vehicles with collision risks will collide. Therefore, it is necessary to screen out preliminary risk targets, and then screen out important risk targets from the preliminary risk targets, and then determine whether to take emergency braking based on the important risk targets.

[0073] In step S100, the first collision time is the collision time between the front of the vehicle and the target two-wheeled vehicle, and the second collision time is the collision time between the rear of the vehicle and the target two-wheeled vehicle. The predicted position information includes: a predicted first lateral position of the front of the target two-wheeled vehicle at the first collision time, a predicted second lateral position of the rear of the target two-wheeled vehicle at the second collision time, a predicted third lateral position of the front of the vehicle at the first collision time, and a predicted fourth lateral position of the rear of the vehicle at the second collision time.

[0074] Since in step S100, whether the target two-wheeled vehicle is on the driving trajectory of the own vehicle is preliminarily determined based on the predicted position information of the own vehicle and the target two-wheeled vehicle at the first collision time and the second collision time, the first collision time and the second collision time between the front of the own vehicle and each target two-wheeled vehicle need to be determined before step S100.

[0075] Exemplarily, the first collision time is obtained according to the longitudinal distance between the front of the vehicle and the center point of the target two-wheeled vehicle, the current longitudinal speed of the vehicle and the current longitudinal speed of the target two-wheeled vehicle; when calculating the first collision time, it can be calculated according to Formula 1, which is:

[0076] ttc front =lgt obs_posn / (V ego_lgt -V obs_lgt )

[0077] In formula 1, lgt obs_posn V is the longitudinal distance between the front of the vehicle and the center point of the target two-wheeled vehicle, ego_lgt is the current longitudinal velocity of the vehicle, V obs_lgt The current longitudinal speed of the target two-wheeler, ttc front is the first collision time; where lgt obs_posn and V obs_lgt All can be obtained through visual perception.

[0078] Visual perception is the data obtained by the camera installed on the vehicle, such as Figure 5 As shown, a camera in this embodiment is usually installed at the position of the rearview mirror on the front windshield of the vehicle. The solution of this embodiment only requires one camera and does not require additional radar or other redundant cameras for assistance.

[0079] Exemplarily, the second collision time is obtained according to the longitudinal distance between the front of the own vehicle and the center point of the target two-wheeled vehicle, the current longitudinal speed of the own vehicle, the current longitudinal speed of the target two-wheeled vehicle, the length of the own vehicle and the length coefficient of the own vehicle. When calculating the second collision time, it can be calculated according to Formula 2, which is:

[0080] ttc real =(lgtobs_posn +ratio length ×ego length ) / (V ego_lgt -V obs_lgt )

[0081] In formula 2, ttc real is the second collision time, lgt obs_posn is the longitudinal distance between the front of the vehicle and the center point of the target two-wheeled vehicle, V ego_lgt The current longitudinal velocity of the vehicle, V obs_lgt The current longitudinal speed of the target two-wheeler, ratio length is the ego length calibration coefficient, ego length is the length of the vehicle.

[0082] Among them, ratio length It is a coefficient set by the user, which is usually a value greater than or equal to 1 and less than or equal to 1.1.

[0083] For example, Figure 6 As shown, step S100 includes steps S110 to S140:

[0084] Step S110, obtaining a first lateral position according to the current lateral position of the target two-wheeled vehicle, the current lateral speed of the target two-wheeled vehicle, the first collision time, and the current lateral acceleration of the target two-wheeled vehicle.

[0085] Among them, the lateral position of the target two-wheeled vehicle, the lateral speed of the target two-wheeled vehicle and the lateral acceleration of the target two-wheeled vehicle can all be obtained through the visual perception of the camera.

[0086] The predicted first lateral position of the front of the target two-wheeled vehicle at the first collision time can be calculated by Formula 3, which is:

[0087] obs_pred lat_front =obs_cur pos_lat +V obs_lat ×ttc front +0.5×a obs_lat ×ttc front 2

[0088] In formula 3, obs_pred lat_front is the first horizontal position, obs_cur pos_lat The current lateral position of the target two-wheeled vehicle, V obs_lat The current lateral speed of the target two-wheeled vehicle, a obs_lat is the current lateral acceleration of the target two-wheeled vehicle.

[0089] Step S120, obtaining a second lateral position according to the current lateral position of the target two-wheeled vehicle, the current lateral speed of the target two-wheeled vehicle, the second collision time and the current lateral acceleration of the target two-wheeled vehicle.

[0090] The predicted second lateral position of the rear end of the target two-wheeled vehicle at the second collision time can be calculated by Formula 4, which is:

[0091] obs_pred lat_real =obs_cur pos_lat +V obs_lat ×ttc real +0.5×a obs_lat ×ttc real 2

[0092] In formula 4, obs_pred lat_real It is the second lateral position.

[0093] Step S130, obtaining a third horizontal position and a fourth horizontal position according to a third-order Bezier curve.

[0094] Among them, the third-order Bezier curve is based on formula 5 and Figure 7 The third lateral position and the fourth lateral position are obtained based on the principle of.

[0095] Formula 5 is: B(t) = (1-t) 3 ×P 0 +3×(1-t) 2 ×P 1 +3×t 2 ×(1-t)×P 2 +t 3 ×P 3

[0096] In formula 5, B(t) is the coordinate of the point at time t.

[0097] Exemplarily, in this embodiment, the predicted third lateral position of the front of the vehicle at the first collision time is calculated by using Formula 6 to Formula 14.

[0098] First, combine P by formula 6 0 The horizontal position of the point and P 0 The lateral velocity prediction P 1 The horizontal position of the point; where P 0 The starting point of the first segment of the perception output path.

[0099] Formula 6 is:

[0100] in, P is the first path of the perception output1 The horizontal position of the point, is the lateral position of the starting point of the first path of the perception output, V 0_lat P 0 lateral velocity.

[0101] Formula 7 is:

[0102] In formula 7, P 2_lat P is the second path of the perception output 2 Horizontal position of the point, ACC 0_lat P 0 The lateral acceleration of the vehicle at time .

[0103] Formula 8 is: curv ego =2×seg_coeff.sec cof +6×seg_coeff.thrd cof ×pos seg .

[0104] In formula 8, curv ego is the running curvature of the vehicle; seg_coeff.sec cof The credibility of the second segment of the path output by perception (visual perception divides the perceived road segment into three segments and outputs it to the algorithm, each segment includes confidence and length); seg_coeff.thrd cof pos is the credibility of the third path of the perception output; seg The length of the road segment output by perception (referring to the length of the road segment corresponding to the perception output, for example, when calculating the information of the first segment of the path, this pos seg is the length of the first paragraph).

[0105] Formula 9 is: Lat acc =V lgt 2 ×curv ego .

[0106] In formula 9, Lat acc is the predicted value of the lateral acceleration of the vehicle during the predicted time period, V lgt is the longitudinal velocity of the vehicle.

[0107] Formula 10 is: heading ego =seg_coeff.first cof +seg_coeff.sec cof ×pos seg ×2+seg_coeff.thrd cof ×pos seg2 ×3.

[0108] Formula 10 is used to calculate the heading angle of the vehicle, where heading ego is the heading angle of the vehicle, seg_coeff.first cof The credibility of the first path of the perception output.

[0109] Formula 11 is: Lat vel =V lgt ×heading ego .

[0110] Lat in formula 11 vel is the predicted lateral velocity of the ego vehicle.

[0111] Formula 12 is: lat pos =seg_coeff.con cof +seg_coeff.first cof ×pos seg +seg_coeff.sec cof ×pos seg 2 +

[0112] seg_coeff.thrd cof ×pos seg 3 .

[0113] In formula 12, lat pos is the predicted lateral position coordinate of the vehicle, seg_coeff.con cof Output the confidence of the entire road for perception.

[0114] The following formula 13 is used to calculate the P in the third path of the third-order Bezier curve. 3 The horizontal position of the point, formula 13 is:

[0115]

[0116] In formula 13, P 3_lat is the horizontal position of point P3 in the third-order Bezier curve, Lat acc is the current lateral acceleration of the vehicle, Lat ve; is the current lateral velocity of the vehicle, P 2_lat is the horizontal position of point P2 in the third-order Bezier curve, P 1_;at is the horizontal position of point P1 in the third-order Bezier curve, lat pos is the current lateral position of the vehicle.

[0117] The third lateral position of the front of the vehicle at the first collision time is predicted by formula 14, which is:

[0118] P ego_;at (ttc front )=(1-ttc front ) 3 ×P 0 +3×ttc front ×(1-ttc front ) 2 ×P 1_lat +3×

[0119] ttc front 2 ×(1-ttc front )×P 2_lat +ttc front 3 ×P 3_lat .

[0120] In formula 14, P ego_lat (ttc front ) is the predicted third lateral position of the front end of the vehicle at the time of the first collision.

[0121] The calculation method of the fourth lateral position of the rear end of the own vehicle at the second collision time is the same as the calculation method of the third lateral position, except that the first collision time between the front end of the own vehicle and the target two-wheeled vehicle is changed to the second collision time between the rear end of the own vehicle and the target two-wheeled vehicle. Similarly, the calculation formula of the fourth lateral position of the rear end of the own vehicle at the second collision time is shown in Formula 15, where Formula 15 is:

[0122] P ego_lat (ttc real )=(1-ttc real ) 3 ×P 0 +3×ttc real ×(1-ttc real ) 2 ×P 1_lat +3×

[0123] ttc real 2 ×(1-ttc real )×P 2_lat +ttc real 3 ×P 3_lat .

[0124] In formula 15, P ego_lat (ttc real ) is the predicted fourth lateral position of the rear end of the vehicle at the second collision time.

[0125] Step S140, preliminarily determining whether the target two-wheeled vehicle is on the driving track of the own vehicle based on the first lateral position, the second lateral position, the third lateral position, the fourth lateral position, the own vehicle width and the target two-wheeled vehicle width.

[0126] For example, Figure 8 As shown, step S140 includes steps S141 to S143:

[0127] Step S141 , predicting a first relative lateral distance between the front of the target two-wheeled vehicle and the front of the own vehicle according to the first lateral position, the third lateral position, the own vehicle width and the target two-wheeled vehicle width.

[0128] In this step, the first relative lateral distance can be determined by formula 16; wherein formula 16 is:

[0129]

[0130] In formula 16, rel_lat_front is the first relative horizontal distance, width ego is the width of the vehicle, width obs The width of the target two-wheeler, obs_pred lat_front is the first lateral position, P ego_lat (ttc front ) is the predicted third lateral position of the front end of the vehicle at the time of the first collision.

[0131] Step S142, predicting a second relative lateral distance between the rear end of the target two-wheeled vehicle and the rear end of the own vehicle based on the second lateral position, the fourth lateral position, the own vehicle width, and the target two-wheeled vehicle width.

[0132] In this step, the second relative lateral distance can be determined by formula 17; wherein formula 17 is:

[0133]

[0134] In formula 16, rel_lat_real is the second relative horizontal distance, width ego is the width of the vehicle, width obs The width of the target two-wheeler obs_pred lat_real is the second lateral position, P ego_lat (ttc real ) is the predicted fourth lateral position of the rear end of the vehicle at the second collision time.

[0135] Step S143: If any one of the first relative lateral distance and the second relative lateral distance is less than zero, it is preliminarily determined whether the target two-wheeled vehicle is on the driving track of the own vehicle.

[0136] The first relative lateral distance and the second relative lateral distance are calculated by step S141 and step S142. In this step, it is determined whether the first relative lateral distance and the second relative lateral distance are less than zero. If one of the first relative lateral distance and the second relative lateral distance is less than 0, the corresponding target two-wheeled vehicle is preliminarily determined to be on the driving trajectory of the vehicle, and the target two-wheeled vehicle is used as a preliminary risk target.

[0137] Step S200, determining the important risk target according to the first collision time and the second collision time of the preliminary risk target, the relative distance between the vehicle and the preliminary risk target, and the relationship between the preliminary risk target and the driving trajectory of the vehicle when taking the collision avoidance action.

[0138] In step S100, a preliminary risk target is determined from the target two-wheeled vehicles. In order to make the prediction more accurate, in this step, an important risk target needs to be determined from the preliminary risk target. When confirming the important risk target, this step takes into account the first collision time, the second collision time, and whether the preliminary risk target takes avoidance measures.

[0139] like Fig. 9 As shown, step S200 includes:

[0140] Step S210: determining whether the first collision time and the second collision time are within a preset collision time range.

[0141] Exemplarily, a preset collision time is set in advance. The setting of the preset collision time is usually set in combination with the driver's reaction speed and the total amount of calculation, and is usually set to 3 seconds. That is, if the first collision time is greater than 0 seconds and less than 3 seconds, or the second collision time is greater than 0 seconds and less than 3 seconds, it is considered that there is a collision risk. It can be understood that if only one of the first collision time and the second collision time is greater than 0 seconds and less than 3 seconds, the preliminary risk target is considered to have a collision risk, and it is necessary to further determine whether it is an important risk target, and then execute step S220 to determine whether the first relative distance between the front of the vehicle and the preliminary risk target and the second relative distance between the rear of the vehicle and the preliminary risk target are within the preset relative distance range. If both the first collision time and the second collision time are not within the preset collision time range, it means that the preliminary risk target has no collision risk, and then execute step S260, and the corresponding preliminary risk target is not regarded as an important risk target.

[0142] After it is determined in step S100 whether the preliminary risk target is an important risk target, step S220 is executed. The preset relative distance in this step is also used to achieve the setting. The preset relative distance can be 50m. Among them, the first relative distance between the head of the vehicle and the preliminary risk target can be calculated by formula 18, which is: ttcfront ×abs(V obs );V in Formula 18 obs is the overall speed of the initial risk target, ttc front ×abs(V obs ) is the first relative distance. The second relative distance between the rear of the vehicle and the preliminary risk target can be calculated by formula 19, which is: ttc real ×abs(V obs );V in Formula 18 obs is the overall speed of the initial risk target ttc real ×abs(V obs ) is the second relative distance. If any of the first relative distance and the second relative distance is less than the preset relative distance, the current preliminary risk target is further judged to be an important risk target. If both the first relative distance and the second relative distance are not less than the preset relative distance, the current preliminary risk target is not further judged to be an important risk target, which means that the current preliminary risk target is relatively safe.

[0143] If any distance value of the first relative distance and the second relative distance is less than the preset relative distance, step S230 is executed. When the preliminary risk target takes a collision avoidance action, it is further determined whether the preliminary risk target is on the driving trajectory of the vehicle according to the preset calculation rule corresponding to the collision avoidance action.

[0144] Since the present application is mainly aimed at two-wheeled vehicles, the collision avoidance actions taken by two-wheeled vehicles are usually deceleration or steering. Therefore, in this embodiment, the preliminary risk target is judged under the conditions of taking deceleration collision avoidance measures or taking steering collision avoidance measures.

[0145] If the deceleration of the preliminary risk target is obtained through visual perception, the calibrated deceleration of the preliminary risk target is combined with the preset calculation rules to determine whether the current preliminary risk target is on the driving trajectory of the vehicle.

[0146] Among them, the preset calculation rule, that is, the preset calculation rule in step S100, is to substitute the calibrated deceleration of the initial risk target that is decelerating into the above formula 1-formula 17, and then obtain whether the corresponding initial risk target is on the driving trajectory of the vehicle. It can be understood that if the initial risk target is taking the approach of decelerating to avoid collision, the calibrated deceleration is substituted into a in formula 3 obs_lat And calculate whether the current preliminary risk target is on the driving trajectory of the vehicle according to Formula 1-Formula 17.

[0147] If the preliminary risk target is obtained through visual perception and a steering method is adopted to avoid collision, the first heading angle of the current preliminary risk target is first determined based on the angle between the current preliminary risk target and the ego vehicle, the curvature of the current preliminary risk target, and the longitudinal distance between the current preliminary risk target and the ego vehicle; then the longitudinal speed of the current preliminary risk target and the lateral speed of the current preliminary risk target are determined based on the speed of the current preliminary risk target and the first heading angle; finally, based on the first heading angle of the current preliminary risk target, the lateral speed of the current preliminary risk target and the longitudinal speed of the current preliminary risk target combined with a preset calculation rule, it is determined whether the current preliminary risk target is on the driving trajectory of the ego vehicle.

[0148] When the preliminary risk target is turned, the heading angle of the preliminary risk target currently turned can be obtained by formula 2, and formula 20 is:

[0149] Heading=obg.m_ang_dir+pre.p_lgt×pre_curv.

[0150] In Formula 20, Heading is the heading angle of the initial risk target, and obg.m_ang_dir is the angle between the initial risk target and the ego vehicle (the angle is as follows Fig.10 In angle), pre.p_lgt is the longitudinal distance of the initial risk target from the vehicle, and pre_curv is the curvature of the initial risk target; among them, obg.m_ang_dir, pre.p_lgt and pre_curv can all be obtained through visual perception.

[0151] The longitudinal speed of the preliminary risk target can be calculated by formula 21, which is:

[0152] Pre.v_lgt=obs.spd×cos(Heading).

[0153] The lateral speed of the preliminary risk target can be calculated by formula 22, which is:

[0154] Pre.v_lat=obs.spd×sin(Heading).

[0155] In Formula 21 and Formula 22, Pre.v_lgt is the longitudinal speed of the preliminary risk target currently turning, Pre.v_lat is the lateral speed of the preliminary risk target currently turning, obs.spd is the speed of the preliminary risk target, and Heading is the heading angle of the preliminary risk target currently turning.

[0156] After calculating the lateral speed of the current turning preliminary risk target and the longitudinal speed of the current turning preliminary risk target, substitute the lateral speed of the current turning preliminary risk target into Formula 3 and substitute the longitudinal speed of the current turning preliminary risk target into Formula 1, and then combine Formulas 1-17 to determine whether the current turning preliminary risk target is on the form trajectory of the vehicle.

[0157] If it is determined in step S230 that the preliminary risk target is on the driving track of the vehicle, then step S240 is executed to determine the relative coordinates of the preliminary risk target according to the relative position coordinate relationship of the preliminary risk target relative to the vehicle, and to determine whether the lateral coordinates of each judgment point of each preliminary risk target are on the driving track of the vehicle according to the relative coordinates, the driving curvature and the curvature radius of the vehicle. If it is determined in step S230 that the preliminary risk target is not on the driving track of the vehicle, then the preliminary risk target will not be an important risk target.

[0158] Step S240 is mainly to determine if Fig.10 Whether the four corner points (A, B, C, and D) of the two-wheeled vehicle shown will fall into the driving trajectory of the vehicle. If any of the four points A, B, C, and D falls into the driving trajectory of the vehicle, the current preliminary risk target is considered to be an important risk target.

[0159] like Fig.11 As shown, step S240 includes steps S241-S242:

[0160] Step S241, calculating the relative position coordinates of the judgment point of the preliminary risk target relative to the coordinate origin through coordinate transformation.

[0161] The judgment point is Fig.10 The coordinate origin is the center point of the two rear wheels of the vehicle. Fig.10 middle is the angle between the vehicle and the initial risk target, Fig.10 Where OE is the shortest distance from the coordinate to the center line of the initial risk target, and OF is the distance from the origin of the coordinate to the horizontal line of the initial risk target.

[0162] The longitudinal coordinate of point B can be obtained by formula 22, which is:

[0163]

[0164] The horizontal coordinate of point B can be obtained by formula 23, which is:

[0165]

[0166] The longitudinal coordinate of point C can be obtained by formula 24, which is:

[0167]

[0168] The horizontal coordinate of point C can be obtained by formula 25, which is:

[0169]

[0170] The longitudinal coordinate of point A can be obtained by formula 26, which is:

[0171]

[0172] The horizontal coordinate of point A can be obtained by formula 27, which is:

[0173]

[0174] The longitudinal coordinate of point D can be obtained by formula 28, which is:

[0175]

[0176] The horizontal coordinate of point D can be obtained by formula 29, which is:

[0177]

[0178] In formula 22-29, obs_pos lat for Fig.10 The distance between OE and obs_pos lgt for Fig.10 The distance between OF and obs width obs_length is the width of the initial risk target and obs_length is the length of the initial risk target.

[0179] Step S242, obtaining the lateral coordinates of each judgment point of each preliminary risk target according to the relative position coordinates of the judgment point of the preliminary risk target relative to the coordinate origin, the driving curvature and the curvature radius of the vehicle.

[0180] Step S243: if the horizontal coordinate of the judgment point is less than 0, it is determined that the current judgment point is on the driving track of the vehicle.

[0181] After the relative coordinates of the four judgment points of the preliminary risk target are calculated by Formula 22-Formula 29, in this step, the curvature (curv) and curvature radius (curv_radius) of the vehicle are combined to determine whether the horizontal coordinates of the four points are on the driving trajectory of the vehicle.

[0182] The horizontal coordinate of point C can be obtained by formula 30 and formula 31, where formula 30 is:

[0183] C lgt_corved =-curv_radius×tan(C lat / (C lat -curv_radius)).

[0184] Formula 31 is: C lat_corved =curv radius -C lgt / sin(C lgt_corved ×curv).

[0185] In Formula 30 and Formula 31, C lgt_corved is the vertical coordinate of point C, lat_corved is the horizontal coordinate of point C.

[0186] Similarly, the horizontal coordinate of point B can be obtained by formula 32 and formula 33, where formula 32 is:

[0187] B lgt_corved =-curv_radius×tan(B lat / (B lat -curv_radius)).

[0188] Formula 33 is: lat_corved =curv radius -B lgt / sin(B lgt_corved ×curv).

[0189] In formula 32 and formula 33, B lgt_corved is the vertical coordinate of point B, lat_corved is the horizontal coordinate of point B.

[0190] Similarly, the horizontal coordinate of point A can be obtained by formula 34 and formula 35, where formula 34 is:

[0191] A lgt_corved =-curv_radius×tan(A lat / (A lat -curv_radius)).

[0192] Formula 35 is: A lat_corved =curv radius -A lgt / sin(A lgt_corved ×curv).

[0193] In formula 34 and formula 35, A lgt_corvedis the vertical coordinate of point A, lat_corved is the horizontal coordinate of point A.

[0194] Similarly, the horizontal coordinate of point D can be obtained by formula 36 and formula 37, where formula 36 is:

[0195] D lgt_corved =-curv_radius×tan(D lat / (D lat -curv_radius)).

[0196] Formula 37 is: D lat_corved =curv radius -D lgt / sin(D lgt_corved ×curv).

[0197] In Formula 36 and Formula 37, D lgt_corved is the vertical coordinate of point D, D lat_corved is the horizontal coordinate of point D.

[0198] After calculating the horizontal coordinates of A, B, C and D through the above formulas 30-37, determine C lat_corved , B lat_corved , A lat_corved and D lat_corved Is it less than 0? If it is less than 0, it means that the point corresponding to the horizontal coordinate less than 0 is on the driving trajectory of the vehicle.

[0199] Step S250: If any judgment point of the preliminary risk target is on the driving trajectory of the vehicle, the current preliminary risk target is regarded as an important risk target.

[0200] If it is determined through the above step S241 (step S241-step S243) that any of the four judgment points in the preliminary risk target is on the driving trajectory of the vehicle, the current preliminary risk target will be taken as an important risk target. If it is determined through the above step S241 (step S241-step S243) that none of the four judgment points in the preliminary risk target is on the driving trajectory of the vehicle, the corresponding preliminary risk target will not be taken as an important risk target.

[0201] Step S300, when the vehicle decelerates to avoid collision with an important risk target, a target deceleration is determined according to a preset deceleration calculation rule, and whether to trigger automatic emergency braking is determined according to the relationship between the target deceleration and the preset deceleration.

[0202] Before step S300, it is first determined whether the driver has taken other collision avoidance actions except deceleration, and the collision avoidance actions include braking, accelerating or turning. When judging whether the driver has avoided collision by braking (in this case, it means avoiding collision by braking and stopping), it can be judged whether the driver has stepped on the brakes according to whether the brake pedal torque is greater than the calibration value. If the driver has stepped on the brakes, AEB is suppressed (no emergency brake is activated) and the driver is allowed to drive autonomously; when judging whether the driver has avoided collision by accelerating, it can be judged according to the acceleration change value of the vehicle. If the acceleration change value is greater than the threshold, it is considered that the driver has stepped on the accelerator pedal and hopes to avoid obstacles by accelerating. At this time, AEB is suppressed and the driver is allowed to drive autonomously; when judging whether the driver has avoided collision by turning, it can be judged according to the steering wheel angle change rate of the vehicle. If the steering wheel angle change rate is greater than the calibrated threshold, it is considered that the driver has quickly turned the steering wheel to avoid obstacles autonomously. At this time, AEB is suppressed and the driver is allowed to drive autonomously.

[0203] Step S300, after determining the important risk targets and determining that the vehicle has not adopted any other collision avoidance actions except deceleration, then in this step it is necessary to calculate the deceleration (target deceleration) required by the vehicle to avoid collision under the current circumstances. If the required target deceleration is greater than or equal to the preset deceleration, it means that if the vehicle adopts the deceleration collision avoidance method, it will not work, and the AEB (automatic emergency braking system) must be directly triggered to stop the vehicle in time to avoid hitting the two-wheeled vehicle in the adjacent lane.

[0204] In this step, collision is avoided by braking, that is, the minimum distance from the important risk target must be greater than 0 at any prediction time, such as Fig.12 The braking of the vehicle shown is divided into two stages: a deceleration stage where jr is a constant value and a deceleration stage where jr is 0; Fig.12 Where a0 is the initial deceleration of the vehicle; ar is the expected deceleration; tj is the time required to decelerate from a0 to ar; jr is the required jerk.

[0205] By integration, we can find out that the displacement of the vehicle changes with time. The integration method is shown in formula 38, which is:

[0206]

[0207] In formula 38, X is the shortest longitudinal distance of the obstacle at the current prediction time.

[0208] After X and t are known, jr can be obtained by formula 39, which is:

[0209]

[0210] In order to make more precise predictions for important risk targets and improve safety, the required jr can be calculated once for each prediction step (50ms) of each important risk target. After obtaining jr, the deceleration required for the current braking can be determined by formula 40, which is: a.neg.lgt=ego.a.lgt+jr×brake_time.

[0211] In the formula, a.neg.lgt is the deceleration required for braking (target deceleration) based on the current distance between the ego vehicle and the important risk target, ego.a.lgt is the longitudinal acceleration of the ego vehicle, and brake_time is a calibration value, which refers to the driver's reaction time plus the execution reaction time from pressing the brake pedal to starting braking.

[0212] In some implementations, when the AEB triggering conditions are met, it is still necessary to add confirmation frames to avoid false triggering. In this embodiment, the confirmation frames can be increased to 5 frames, that is, if the triggering conditions are met for 5 consecutive times, the AEB instruction is formally issued to the actuator.

[0213] The embodiment of the present application only needs to install one camera on the self-vehicle to implement the method of the embodiment. In the embodiment, when the self-vehicle turns, in order to avoid colliding with the target two-wheeled vehicle traveling in the opposite direction of the adjacent lane, the embodiment of the present application first determines a preliminary risk target from the target two-wheeled vehicles. Further, the important risk target is determined by the first collision time, the second collision time, the relative distance between the self-vehicle and the preliminary risk target, the relationship between the preliminary risk target and the driving trajectory of the self-vehicle when taking the collision avoidance action, and the relationship between the longitudinal coordinate of the preliminary risk target and the lateral coordinate of the preliminary risk target and the driving trajectory of the self-vehicle. Further, after the important risk target is determined, and when the self-vehicle does not take the collision avoidance action, the embodiment of the present application calculates the deceleration required by the self-vehicle in the current situation to avoid the collision. If the required target deceleration reaches the preset deceleration, it means that if the self-vehicle adopts the deceleration collision avoidance method, it is not feasible, and the AEB (automatic emergency braking system) needs to be directly triggered to stop the self-vehicle in time to avoid colliding with the two-wheeled vehicle in the opposite adjacent lane. The embodiment of the present application determines two-wheeled vehicles with a higher risk of collision step by step in this way, thereby avoiding the problem of large amount of calculation caused by calculating whether AEB needs to be triggered for target two-wheeled vehicles traveling in opposite directions in adjacent lanes. By judging whether AEB needs to be triggered for important risk targets, the automatic emergency braking judgment is more accurate.

[0214] Fig.13 A schematic diagram of the structure of a vehicle collision avoidance device according to an embodiment of the present application is shown. Exemplarily, the vehicle collision avoidance device comprises:

[0215] The preliminary risk target determination module 100 is used to calculate the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time according to a preset calculation rule when the self-vehicle turns, and preliminarily determine whether the target two-wheeled vehicle is on the driving track of the self-vehicle according to the predicted position information, and take the target two-wheeled vehicle preliminarily determined to be on the driving track of the self-vehicle as the preliminary risk target; wherein the first collision time is the collision time between the front of the self-vehicle and the target two-wheeled vehicle, and the second collision time is the collision time between the rear of the self-vehicle and the target two-wheeled vehicle;

[0216] The important risk target determination module 200 is used to determine the important risk target according to the first collision time of the preliminary risk target, the second collision time, the relative distance between the ego vehicle and the preliminary risk target, the relationship between the preliminary risk target and the driving track of the ego vehicle when taking a collision avoidance action, and the relationship between the longitudinal coordinate of the preliminary risk target and the lateral coordinate of the preliminary risk target and the driving track of the ego vehicle;

[0217] The automatic emergency brake triggering module 300 is used to determine the target deceleration according to the preset deceleration calculation rule when the vehicle decelerates to avoid collision with an important risk target, and determine whether to trigger the automatic emergency brake according to the relationship between the target deceleration and the preset deceleration.

[0218] It can be understood that the device of this embodiment corresponds to the vehicle collision avoidance method of the above embodiment, and the options in the above embodiment are also applicable to this embodiment, so they will not be described repeatedly here.

[0219] The present application also provides a terminal device. Exemplarily, the terminal device includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program, thereby enabling the terminal device to execute the functions of each module in the above-mentioned vehicle collision avoidance method or the above-mentioned vehicle collision avoidance device.

[0220] Among them, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU) and a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or at least one of other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc., which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the present application.

[0221] The memory may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc. The memory is used to store a computer program, and the processor may execute the computer program accordingly after receiving an execution instruction.

[0222] The present application also provides a computer-readable storage medium for storing the computer program used in the above-mentioned terminal device. For example, the computer-readable storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0223] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products 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 a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, 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 structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, 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.

[0224] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0225] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.

[0226] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A vehicle collision avoidance method, characterized in that: include: When the self-vehicle turns, the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time is calculated according to a preset calculation rule, and whether the target two-wheeled vehicle is on the driving track of the self-vehicle is preliminarily determined according to the predicted position information, and the target two-wheeled vehicle preliminarily determined to be on the driving track of the self-vehicle is taken as a preliminary risk target; wherein, the first collision time is the collision time between the front of the self-vehicle and the target two-wheeled vehicle, and the second collision time is the collision time between the rear of the self-vehicle and the target two-wheeled vehicle; Determine an important risk target according to the first collision time of the preliminary risk target, the second collision time, the relative distance between the ego vehicle and the preliminary risk target, and the relationship between the preliminary risk target and the driving trajectory of the ego vehicle when taking a collision avoidance action; When the self-vehicle decelerates to avoid collision with the important risk target, a target deceleration is determined according to a preset deceleration calculation rule, and whether to trigger automatic emergency braking is determined according to a relationship between the target deceleration and the preset deceleration.

2. The vehicle collision avoidance method according to claim 1, characterized in that: The predicted position information includes: a predicted first lateral position of the front of the target two-wheeled vehicle at the first collision time, a predicted second lateral position of the rear of the target two-wheeled vehicle at the second collision time, a predicted third lateral position of the front of the own vehicle at the first collision time, and a predicted fourth lateral position of the rear of the own vehicle at the second collision time.

3. The vehicle collision avoidance method according to claim 1, characterized in that: The method further comprises: calculating the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time according to a preset calculation rule, and preliminarily determining whether the target two-wheeled vehicle is on the driving track of the self-vehicle according to the predicted position information. Obtaining the first collision time according to the longitudinal distance between the front of the own vehicle and the center point of the target two-wheeled vehicle, the current longitudinal speed of the own vehicle and the current longitudinal speed of the target two-wheeled vehicle; The second collision time is obtained according to the longitudinal distance between the front end of the own vehicle and the center point of the target two-wheeled vehicle, the current longitudinal speed of the own vehicle, the current longitudinal speed of the target two-wheeled vehicle, the length of the own vehicle and the length coefficient of the own vehicle.

4. The vehicle collision avoidance method according to claim 2, characterized in that: The step of calculating the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time according to a preset calculation rule, and preliminarily determining whether the target two-wheeled vehicle is on the driving track of the self-vehicle according to the predicted position information, includes: Acquire the first lateral position according to the current lateral position of the target two-wheeled vehicle, the current lateral speed of the target two-wheeled vehicle, the first collision time, and the current lateral acceleration of the target two-wheeled vehicle; acquiring the second lateral position according to the current lateral position of the target two-wheeled vehicle, the current lateral speed of the target two-wheeled vehicle, the second collision time and the current lateral acceleration of the target two-wheeled vehicle; Acquire the third lateral position and the fourth lateral position according to a third-order Bezier curve; It is preliminarily determined whether the target two-wheeled vehicle is on the driving track of the own vehicle based on the first lateral position, the second lateral position, the third lateral position, the fourth lateral position, the own vehicle width and the target two-wheeled vehicle width.

5. The vehicle collision avoidance method according to claim 4, characterized in that: The preliminarily determining whether the target two-wheeled vehicle is on the driving track of the own vehicle based on the first lateral position, the second lateral position, the third lateral position, the fourth lateral position, the own vehicle width and the target two-wheeled vehicle width includes: Predicting a first relative lateral distance between the front of the target two-wheeled vehicle and the front of the own vehicle based on the first lateral position, the third lateral position, the own vehicle width, and the target two-wheeled vehicle width; predicting a second relative lateral distance between the rear end of the target two-wheeled vehicle and the rear end of the own vehicle based on the second lateral position, the fourth lateral position, the own vehicle width, and the target two-wheeled vehicle width; If any one of the first relative lateral distance and the second relative lateral distance is less than zero, it is preliminarily determined whether the target two-wheeled vehicle is on the driving track of the own vehicle.

6. The vehicle collision avoidance method according to claim 1, characterized in that: Determining the important risk target according to the first collision time of the preliminary risk target, the second collision time, the relative distance between the vehicle and the preliminary risk target, and the relationship between the preliminary risk target and the driving trajectory of the vehicle when taking a collision avoidance action, includes: Determining whether the first collision time and the second collision time are within a preset collision time range; If yes, determining whether the first relative distance between the front of the vehicle and the preliminary risk target and the second relative distance between the rear of the vehicle and the preliminary risk target are within a preset relative distance range; If so, when the preliminary risk target takes a collision avoidance action, continue to determine whether the preliminary risk target is on the driving track of the vehicle according to a preset calculation rule corresponding to the collision avoidance action; If yes, then determine the relative coordinates of the preliminary risk target according to the relative position coordinate relationship of the preliminary risk target with respect to the ego vehicle, and judge whether the lateral coordinates of each judgment point of each preliminary risk target are on the driving track of the ego vehicle according to the relative coordinates, the driving curvature and the curvature radius of the ego vehicle; If any of the judgment points of the preliminary risk targets is on the driving trajectory of the vehicle, the current preliminary risk target is taken as an important risk target.

7. The vehicle collision avoidance method according to claim 6, characterized in that: When the preliminary risk target takes a collision avoidance action, continuing to determine whether the preliminary risk target is on the driving trajectory of the vehicle according to a preset calculation rule corresponding to the collision avoidance action includes: If the preliminary risk target decelerates, combining the calibrated deceleration of the preliminary risk target with the preset calculation rule to determine whether the preliminary risk target is currently on the driving trajectory of the vehicle; If the preliminary risk target turns, determine a first heading angle of the preliminary risk target according to the angle between the preliminary risk target and the vehicle, the curvature of the preliminary risk target, and the longitudinal distance between the preliminary risk target and the vehicle; Determining the longitudinal speed of the current preliminary risk target and the lateral speed of the current preliminary risk target according to the speed of the current preliminary risk target and the first heading angle; According to the first heading angle of the current preliminary risk target, the lateral speed of the current preliminary risk target and the longitudinal speed of the current preliminary risk target in combination with a preset calculation rule, it is determined whether the current preliminary risk target is on the driving trajectory of the vehicle.

8. The vehicle collision avoidance method according to claim 6, characterized in that: The determining of the relative coordinates of the preliminary risk target according to the relative position coordinate relationship of the preliminary risk target with respect to the vehicle, and judging whether the lateral coordinates of each judgment point of each preliminary risk target is on the driving track of the vehicle according to the relative coordinates, the driving curvature of the vehicle and the curvature radius, comprises: Calculate the relative position coordinates of the judgment point of the preliminary risk target relative to the coordinate origin through coordinate transformation; Obtaining the lateral coordinates of each of the judgment points of each of the preliminary risk targets according to the relative position coordinates of the judgment point of the preliminary risk target relative to the coordinate origin, the travel curvature of the vehicle and the curvature radius; If the lateral coordinate of the judgment point is less than 0, it is determined that the current judgment point is on the driving track of the vehicle.

9. A vehicle collision avoidance device, characterized in that: include: A preliminary risk target determination module is used to calculate the predicted position information of the self-vehicle and the target two-wheeled vehicle at the first collision time and the second collision time according to a preset calculation rule when the self-vehicle turns, and preliminarily determine whether the target two-wheeled vehicle is on the driving track of the self-vehicle according to the predicted position information, and take the target two-wheeled vehicle preliminarily determined to be on the driving track of the self-vehicle as the preliminary risk target; wherein the first collision time is the collision time between the front of the self-vehicle and the target two-wheeled vehicle, and the second collision time is the collision time between the rear of the self-vehicle and the target two-wheeled vehicle; An important risk target determination module, configured to determine an important risk target according to the first collision time of the preliminary risk target, the second collision time, the relative distance between the ego vehicle and the preliminary risk target, and the relationship between the preliminary risk target and the driving trajectory of the ego vehicle when taking a collision avoidance action; The automatic emergency brake triggering module is used to determine the target deceleration according to the preset deceleration calculation rule when the self-vehicle decelerates to avoid collision with the important risk target, and determine whether to trigger the automatic emergency brake according to the relationship between the target deceleration and the preset deceleration.

10. A terminal device, characterized in that: The terminal device comprises a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the vehicle collision avoidance method according to any one of claims 1 to 8.

Images