Vehicle collision avoidance method, device and equipment and storage medium

Abstract

The invention relates to the technical field of intelligent driving, and discloses a vehicle collision avoidance method, device and equipment and a storage medium, and the method comprises the steps: when a vehicle needs to steer, judging whether a first target object is a risk target according to the motion state of the vehicle and the motion state, obtained through a visual perception device, of the first target object on a steering side adjacent lane; if yes, when any one target radar senses a second target object of the adjacent lane on the steering side, whether the second target object sensed by the corresponding target radar and the risk target are the same target object or not is judged; wherein the target radars are two radars arranged at the vehicle corner position of the steering side of the vehicle; if yes, judging whether to trigger emergency braking or not according to a preset rule when the visual perception device cannot perceive the risk target and any radar in the target radars still can perceive the risk target in the continuous walking process of the vehicle. The method can effectively avoid the target object running in the same direction when the vehicle turns.

Description

Technical Field

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

[0002] With the increase in the number of vehicles, the risk of traffic accidents is also increasing. When a vehicle turns, the driver often fails to notice a two-wheeled vehicle traveling in the same direction in the adjacent lane on the turning side, which may cause a traffic accident and result in loss of life or property. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a vehicle collision avoidance method, device, equipment and storage medium, which can effectively prevent the vehicle from colliding with a two-wheeled vehicle or a three-wheeled vehicle during a turn.

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

[0005] When the vehicle needs to turn, judging whether the first target object is a risk target according to the motion state of the vehicle and the motion state of the first target object in the lane adjacent to the turning side acquired by the visual perception device;

[0006] If so, when any target radar senses a second target in the lane adjacent to the turning side, it is determined whether the second target sensed by the corresponding target radar and the risk target are the same target; wherein the first radar and the second radar are two radars arranged at the vehicle corner position on the turning side of the vehicle;

[0007] If so, when the vehicle continues to move and the visual perception device cannot perceive the risk target but the target radar can still perceive the risk target, it is determined whether to trigger emergency braking according to preset rules.

[0008] In some embodiments, judging whether the first target object is a risk target according to the motion state of the vehicle and the motion state of the first target object in the lane adjacent to the turning side acquired by the visual perception device includes:

[0009] Acquire a first longitudinal position of the vehicle at a first prediction time according to a first longitudinal velocity and a first longitudinal acceleration of the vehicle;

[0010] Acquire a first lateral position of the vehicle at the first prediction time according to a first lateral velocity and a first lateral acceleration of the vehicle;

[0011] Acquire a second longitudinal position of the first target object at the first predicted time according to the second longitudinal velocity and the second longitudinal acceleration of the first target object and the current longitudinal position of the first target object;

[0012] Acquire a second lateral position of the first target object at the first predicted time according to the second lateral velocity and the second lateral acceleration of the first target object and the current lateral position of the first target object;

[0013] Whether the first target object is the risk target is determined according to the first longitudinal position, the second longitudinal position, the first lateral position, the second lateral position, and the turning direction of the vehicle.

[0014] In some embodiments, the determining whether the second target object sensed by the corresponding target radar and the risk target are the same target object includes:

[0015] Determining a first relative coordinate of the risk target relative to the coordinate origin;

[0016] Determine a second relative coordinate corresponding to the target radar relative to the coordinate origin;

[0017] Whether the second target and the risk target are the same target is determined according to the first relative coordinates, the second relative coordinates and the position coordinates of the second target returned by the corresponding radar.

[0018] In some embodiments, determining the first relative coordinate of the risk target relative to the coordinate origin includes:

[0019] Determine a first longitudinal coordinate and a second longitudinal coordinate according to the first longitudinal distance, the width of the risk target and the target angle;

[0020] Determine a first transverse coordinate and a second transverse coordinate according to the first transverse distance, the width of the risk target and the target angle;

[0021] Determine a third longitudinal coordinate and a fourth longitudinal coordinate according to the first longitudinal distance, the width of the risk target, the target angle, and the length of the risk target;

[0022] Determining a third transverse coordinate and a fourth transverse coordinate according to the first transverse distance, the width of the risk target, the target angle, and the length of the risk target;

[0023] The first longitudinal coordinate and the first transverse coordinate are the first relative coordinates corresponding to the first point; the second longitudinal coordinate and the second transverse coordinate are the first relative coordinates corresponding to the second point; the third longitudinal coordinate and the third transverse coordinate are the first relative coordinates corresponding to the third point; the fourth longitudinal coordinate and the fourth transverse coordinate are the first relative coordinates corresponding to the fourth point;

[0024] The first point and the second point are points at the tail of the risk target frame close to and away from the corresponding points of the vehicle; the third point and the fourth point are points at the head of the risk target frame close to and away from the corresponding points of the vehicle; the risk target frame is a rectangular frame composed of the width and length of the risk target;

[0025] The first longitudinal distance is the longitudinal distance between the center point of the tail of the risk target and the origin of the vehicle coordinate system; the first lateral distance is the lateral distance between the center point of the tail of the risk target and the origin of the vehicle coordinate system; the target angle is the angle formed by a line in the longitudinal direction of the vehicle and a line in the longitudinal direction of the risk target.

[0026] In some embodiments, determining the second relative coordinates of the target radar relative to the coordinate origin includes:

[0027] According to the longitudinal coordinate of the real-time position of the vehicle, the wheelbase of the vehicle calibrated by the target radar, the heading angle of the vehicle, and the width of the vehicle calibrated by the target radar, Determine the radar longitudinal coordinate of the corresponding radar relative to the coordinate origin;

[0028] According to the lateral coordinates of the real-time position of the vehicle, the wheelbase of the vehicle calibrated by the target radar, the heading angle of the vehicle, and the width of the vehicle calibrated by the target radar, Determine the radar lateral coordinates of the corresponding radar relative to the coordinate origin;

[0029] The radar longitudinal coordinate and the radar transverse coordinate constitute the second relative coordinate.

[0030] In some embodiments, judging whether the second target and the risk target are the same target according to the first relative coordinates, the second relative coordinates, and the position coordinates of the second target returned by the corresponding radar includes:

[0031] Acquire third relative coordinates of the first point, the second point, the third point, and the fourth point of the second target object relative to the coordinate origin according to the position coordinates of the first point, the second point, the third point, the fourth point, and the second relative coordinates returned by the corresponding radar;

[0032] The first relative coordinate and the third relative coordinate are compared, and if the difference between the corresponding points is within a preset range, it is determined that the second target object and the risk target are the same target object.

[0033] In some embodiments, determining whether to trigger emergency braking according to a preset rule includes:

[0034] Obtaining a third lateral position of the vehicle relative to the current position at a second prediction time according to the current third lateral speed and third lateral acceleration of the vehicle;

[0035] Acquire a fourth lateral position of the risk target relative to the current position of the vehicle at the second prediction time according to the fourth lateral speed and the fourth lateral acceleration of the risk target acquired by the target radar;

[0036] determining whether there is a collision risk according to the third lateral position and the fourth lateral position;

[0037] If yes, whether to trigger emergency braking is determined according to the vehicle speed and the distance between the risk target and the vehicle returned by the target radar.

[0038] In a second aspect, an embodiment of the present application provides a vehicle collision avoidance device, comprising:

[0039] A risk target determination module, used for determining whether the first target object is a risk target according to the motion state of the vehicle and the motion state of the first target object in the lane adjacent to the turning side acquired by the visual perception device when the vehicle needs to turn.

[0040] A judgment module, for judging whether, when any target radar senses a second target in the lane adjacent to the turning side, the second target sensed by the corresponding target radar and the risk target are the same target; wherein the target radars are two radars arranged at the vehicle corner position on the turning side of the vehicle;

[0041] The emergency braking determination module is used to determine whether to trigger emergency braking according to preset rules if, during the vehicle's continued movement, the visual perception device cannot perceive the risk target and any one of the target radars can still perceive the risk target.

[0042] In a third aspect, an embodiment of the present application provides a vehicle, comprising 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.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when executed on a processor, implements the above-mentioned vehicle collision avoidance method.

[0044] The embodiments of the present application have the following beneficial effects:

[0045] In the present application, when the self-vehicle needs to turn, the risk target in the target object is first determined according to the movement state of the self-vehicle and the target object. After the risk target is determined, since the self-vehicle and the risk target may continue to move, the risk target may be lost during the walking process. Therefore, in the present embodiment, when both the self-vehicle and the radar can perceive the target object, it is determined whether the target object perceived by the self-vehicle and the radar is the same through the position of the risk target perceived by the self-vehicle and the position of the target perceived by the radar. If so, it means that the risk target is not lost. Then, when the self-vehicle and the target object continue to move, when the visual perception device cannot perceive the risk target but the target radar can still perceive the risk target, it means that the front of the self-vehicle has exceeded the risk target. At this time, it is determined whether to trigger emergency braking according to the preset rules to avoid collision between the self-vehicle and the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] 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.

[0047] Figure 1 A schematic diagram of a working condition scenario in which a target object traveling in the same direction is present in an adjacent lane when the vehicle turns in an embodiment of the present application;

[0048] Figure 2 A schematic diagram of a radar installed on a vehicle according to an embodiment of the present application is shown;

[0049] Figure 3 A first flow chart of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0050] Figure 4 A schematic diagram of a first scene of a vehicle and a target object in an embodiment of the present application is shown;

[0051] Figure 5 A second scene schematic diagram of the vehicle and the target object in an embodiment of the present application is shown;

[0052] Figure 6 A second flow chart of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0053] Figure 7 A third flow chart of the vehicle collision avoidance method according to an embodiment of the present application is shown;

[0054] Figure 8 A structural schematic diagram of a vehicle collision avoidance device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0055] 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.

[0056] 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.

[0057] 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.

[0058] 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.

[0059] 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.

[0060] The vehicle collision avoidance method proposed in this embodiment is mainly aimed at Figure 1 The following figure shows the working condition when the vehicle is turning (left or right) and there is a target object traveling in the same direction in the adjacent lane. Figure 1 The driving condition shown in is that the vehicle travels from point A to point A', and the target object travels from point B to point B' or continues to move forward, and the vehicle and the target object may collide at point C. The target object in this condition can be a bicycle, an electric bicycle, an electric motorcycle, a tricycle, an electric tricycle, etc.

[0061] The vehicle used in the vehicle collision avoidance method of this embodiment is a vehicle equipped with a radar, such as Figure 2 As shown in , the vehicle needs to have at least two radars installed at the two corners of the front end of the vehicle, such as Figure 2 In the embodiment, the two radars installed at the left corner of the front end of the vehicle are radar FL and radar FLS, and the two radars installed at the right corner are radar FR and radar FRS. It can be understood that when the vehicle turns right, the target radars are radar FR and radar FRS; when the vehicle turns left, the target radars are radar FL and radar FLS. In addition, since the vehicle collision avoidance method of this embodiment also needs to adopt visual perception, and only one visual perception device is required, the vehicle of this embodiment only needs to install a camera at the rearview mirror for visual perception.

[0062] Among them, for the driving safety of the vehicle, multiple other radars can be installed in the vehicle, such as Figure 2 The radar FML and radar FMR at the front of the vehicle, and the radar RLS, radar RL, radar RML, radar RMR, radar RR and radar RRS at the rear of the vehicle. The sensing distance and field of view (FOV angle) of the radar and camera installed in the vehicle are shown in the following table:

[0063] Detection equipment category FOV angle Perception distance Forward visual perception Camera 110° 200M FL Short-range ultrasonic radar 80° 0.2M-2M FML Short-range ultrasonic radar 80° 0.2M-2M FMR Short-range ultrasonic radar 80° 0.2M-2M FR Short-range ultrasonic radar 80° 0.2M-2M FLS Long range ultrasonic radar 90° 0.25–4M FRS Long range ultrasonic radar 90° 0.25–4M RLS Long range ultrasonic radar 90° 0.25–4M RRS Long range ultrasonic radar 90° 0.25–4M RL Short-range ultrasonic radar 80° 0.2M-2M RML Short-range ultrasonic radar 80° 0.2M-2M RMR Short-range ultrasonic radar 80° 0.2M-2M RR Short-range ultrasonic radar 80° 0.2M-2M

[0064] The vehicle collision avoidance method is described below in conjunction with some specific embodiments.

[0065] Figure 3 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:

[0066] Step S100, when the vehicle needs to turn, judging whether the first target object is a risk target according to the motion state of the vehicle and the motion state of the first target object in the lane adjacent to the turning side obtained by the visual perception device.

[0067] The motion state includes, but is not limited to, motion speed (lateral speed and longitudinal speed), acceleration (lateral acceleration and longitudinal acceleration), and the like.

[0068] When the vehicle is moving, if the steering is turned on, it means that the vehicle needs to turn. The target object located on the corresponding side of the vehicle can be determined to be the first target object that may be risky according to the situation of the turned-on turn signal. Since the target objects targeted by this embodiment are two-wheeled vehicles (bicycles, electric bicycles, electric motorcycles, etc.) and tricycles, the speed of the target object is usually slower than the speed of the vehicle, and when turning is required, the turn signal is usually turned on in advance. Therefore, when the turn signal is just turned on, the first target object that may be risky should be in front of the vehicle. At this time, the visual perception device of the vehicle can perceive the first target object. In this step, the trajectory of the first target object can be predicted by the motion state of the first target object perceived by the visual perception device, and the trajectory of the vehicle can be predicted by the running state of the vehicle. According to the predicted trajectory of the vehicle and the trajectory of the first target object, it is determined whether the first target object is a risk target. It can be understood that there may be multiple first targets, so it is necessary to predict the trajectory of each first target object and judge whether the corresponding first target object is a risk target in combination with the predicted trajectory of the vehicle. In order to distinguish each first target object, the target ID of the first target object can be fused in the perception information.

[0069] In some implementations, step S100 includes steps S110-S150:

[0070] Step S110 , obtaining a first longitudinal position of the vehicle at a first prediction time according to a first longitudinal velocity and a first longitudinal acceleration of the vehicle.

[0071] Among them, the first prediction time is usually less than or equal to 3 seconds. In this embodiment, the position information of the vehicle and the position information of the first target object can be predicted once at a certain interval, such as once every 0.5s, once every 1S, once every 1.5s, once every 2s, etc. It can be understood that the above setting of the first preset time is illustrative, and in actual operation, it can be set as needed.

[0072] In this step, the first longitudinal position can be calculated according to Formula 1, which is:

[0073] In the formula, ped_pos_lgt is the first longitudinal position of the vehicle at the first predicted time, t is the first predicted time, V lgt is the first longitudinal velocity of the vehicle, a lgt is the first longitudinal acceleration of the vehicle.

[0074] Step S120: acquiring a first lateral position of the vehicle at a first prediction time according to a first lateral velocity and a first lateral acceleration of the vehicle.

[0075] In this step, the first lateral position can be calculated according to Formula 1, and Formula 2 is:

[0076] In the formula, ped_pos_lat is the first lateral position of the vehicle at the first predicted time, t is the first predicted time, V lat is the first lateral velocity of the vehicle, a lat The first lateral acceleration of the vehicle.

[0077] It should be noted that, in this embodiment, the longitudinal direction is the direction of the vehicle (which can also be understood as the forward direction of the vehicle), and the transverse direction is a direction perpendicular to the longitudinal direction.

[0078] Step S130 , obtaining a second longitudinal position of the first target at a first prediction time according to the second longitudinal velocity and the second longitudinal acceleration of the first target and the current longitudinal position of the first target.

[0079] In this step, the second longitudinal position can be calculated according to Formula 3, which is:

[0080] In the formula, ped_obs_pos_lgt is the predicted second longitudinal position of the first target at the first prediction time, t is the first prediction time, V obs_lgt is the second longitudinal velocity of the first target, a obs_lgt is the second longitudinal acceleration of the first target object, and ped_obs_pos_lgt0 is the current longitudinal position of the first target object.

[0081] Step S140 , obtaining a second lateral position of the first target at a first prediction time according to the second lateral velocity and the second lateral acceleration of the first target and the current lateral position of the first target.

[0082] In this step, the second lateral position can be calculated according to Formula 4, which is:

[0083] In the formula, ped_obs_pos_lat is the predicted second lateral position of the first target at the first prediction time, t is the first prediction time, V obs_lat is the second lateral velocity of the first target, a obs_lat is the second lateral acceleration of the first target object, and ped_obs_pos_lat0 is the current lateral position of the first target object.

[0084] It should be noted that when calculating the second longitudinal position and the second lateral position of the first target, the position of the midpoint of the rear overhang of the first target is calculated, that is, Figure 4 The intersection of the X-axis and Y-axis of the target object shown.

[0085] Step S150 , determining whether the first target object is a risky target according to the first longitudinal position, the second longitudinal position, the first lateral position, the second lateral position and the turning direction of the vehicle.

[0086] Generally speaking, if the vehicle and the first target object are getting closer and closer, there is a risk of collision. Therefore, in this step, the difference between the second longitudinal position and the first longitudinal position, as well as the difference between the second lateral position and the first lateral position, can be used to determine whether the current first target object is a risky target, combined with the turning direction of the vehicle.

[0087] It can be understood that at any first prediction time, if the vehicle is turning right, if ped_obs_pos_lgt-ped_pos_lgt≤0, and ped_obs_pos_lat-ped_pos_lat≥0, it means that the vehicle has a collision risk with the first target, and the first target is determined to be a risk target. If the vehicle is turning left, if ped_obs_pos_lgt-ped_pos_lgt≤0, and ped_obs_pos_lat-ped_pos_lat≤0, it means that the vehicle has a collision risk with the first target, and the first target is determined to be a risk target.

[0088] like Figure 4 , Figure 5 As shown, the car is turning right, the x-axis is the longitudinal direction, and the y-axis is the transverse direction. Figure 4 In the horizontal direction, moving to the left is positive and moving to the right is negative. In the vertical direction, moving upward is positive and moving downward is negative. Since the ego vehicle and the first target object calculate the first longitudinal position, the first lateral position, the second longitudinal position and the second lateral position respectively according to their current positions, the comparison is the moving distance of the ego vehicle and the first target object from their current positions to the predicted positions. Figure 4 The middle is the current position of the vehicle and the first target. The initial longitudinal position of the vehicle is 0, and the lateral position is also 0. The initial longitudinal position of the first target is 3, and the lateral position is -2.8. Figure 5 is the predicted position of the vehicle and the first target at the first prediction time. At this time, the longitudinal position of the vehicle is 6.5 and the lateral position is -3.0, and the longitudinal position of the first target is 6.4 and the lateral position is -2.8.

[0089] It should be noted that when the first target object is determined in step S100, the lateral distance between the target object and the vehicle is also required. If the lateral distance is greater than the preset distance, it means that the target object is far away from the vehicle and will not be calculated as the first target object. For example, the preset distance can be 3 meters.

[0090] The determination of the risk target in step S100 can be applied to Figure 1 When the vehicle is at point D' and the target is at point D, the ultrasonic radars FR and FRS cannot perceive the target, but the visual perception device can perceive the target; this step S100 is also applicable to Figure 1 When the ego vehicle is at point E' and the target object is at point E, the visual perception device can still perceive the target object, and at least one of the ultrasonic radars FR and FRS can perceive the status of the target object. It can be understood that Figure 1 The vehicle shown is turning right. If the vehicle turns left, the situation is the same and no further explanation is given.

[0091] If it is determined in step S100 that there is no risk target, the process ends.

[0092] After the risk target is determined in step S100, step S200 is executed to determine whether the second target perceived by the corresponding target radar and the risk target are the same target when any target radar perceives the second target in the lane adjacent to the turning side.

[0093] It can be understood that if the vehicle turns right, the target radars are radars FR and FRS, and if the vehicle turns left, the target radars are radars FL and FLS.

[0094] Step S200 is mainly to determine whether the identified risk target is lost. If it is lost, the process ends. If it is not lost, step S300 is executed.

[0095] In step S200, four points of the risk target are first determined, wherein the first point and the second point are points at the tail of the risk target frame close to and away from the vehicle; the third point and the fourth point are points at the head of the risk target frame close to and away from the vehicle; the risk target frame is a rectangular frame composed of the width and length of the risk target, so the position of the risk target can be determined based on these four points. In addition, when the second target is determined by radar, the position of the second target is also determined by determining the four points of the second target.

[0096] In step S200, first, the four-point position information of the risk target of the visual perception device is converted into a first relative coordinate relative to the coordinate origin through coordinate conversion; and the second relative coordinate of the target radar relative to the coordinate far point is calculated at the same time. According to the relative coordinate of the target radar relative to the coordinate far point and the coordinate information of the second target object returned by the radar, the third relative coordinate of the second target object relative to the coordinate origin can be obtained. Finally, the first relative coordinate is compared with the third relative coordinate to see whether they overlap, and then it can be determined whether the risk target detected by the visual perception device and the second target object perceived by the target radar are the same target. If they are the same target, it means that the risk target is not lost.

[0097] For example, Figure 6 As shown, step S200 includes steps S210 to S230:

[0098] Step S210, determining a first relative coordinate of the risk target relative to the coordinate origin.

[0099] The purpose of this step is to determine the first relative coordinates of the four points of the risk target relative to the coordinate origin, where Figure 4 As shown, the origin of the coordinate system is the center point of the rear suspension of the vehicle.

[0100] In some embodiments, when describing step S210, it should be first explained that the first longitudinal coordinate and the first transverse coordinate are the first relative coordinates corresponding to the first point; the second longitudinal coordinate and the second transverse coordinate are the first relative coordinates corresponding to the second point; the third longitudinal coordinate and the third transverse coordinate are the first relative coordinates corresponding to the third point; the fourth longitudinal coordinate and the fourth transverse coordinate are the first relative coordinates corresponding to the fourth point.

[0101] The first point and the second point are the points where the tail of the risk target frame is close to and far from the vehicle, that is, the first point and the second point are Figure 4 The third and fourth points are the points where the head of the risk target frame approaches and moves away from the vehicle, respectively. Figure 4 Point A and point D in the middle; the risk target frame is a rectangular frame composed of the width and length of the risk target.

[0102] The first longitudinal distance is the longitudinal distance between the center point of the risk target tail and the origin of the vehicle coordinate system (i.e. Figure 4 The first lateral distance is the lateral distance between the center point of the risk target tail and the origin of the vehicle coordinate system (i.e. Figure 4 The horizontal distance from point O' to point O, that is, the distance of O'E); the target angle is the angle formed by the line in the longitudinal direction of the vehicle and the line in the longitudinal direction of the risk target (such as Figure 5 middle ).

[0103] In step S210, the first longitudinal coordinate and the second longitudinal coordinate are determined according to the first longitudinal distance, the width of the risk target and the target angle; the first transverse coordinate and the second transverse coordinate are determined according to the first transverse distance, the width of the risk target and the target angle; the third longitudinal coordinate and the fourth longitudinal coordinate are determined according to the first longitudinal distance, the width of the risk target, the target angle and the length of the risk target; the third transverse coordinate and the fourth transverse coordinate are determined according to the first transverse distance, the width of the risk target, the target angle and the length of the risk target.

[0104] In calculating the first point ( Figure 4 When the first longitudinal coordinate of point B in the middle is calculated, it can be calculated according to formula 5, which is

[0105] In calculating the first point ( Figure 4 When the first horizontal coordinate of point B in the middle is calculated, it can be calculated according to formula 6, which is

[0106] When calculating the second point ( Figure 4 The second longitudinal coordinate of point C in the middle can be calculated according to formula 7, which is

[0107] When calculating the second point ( Figure 4 The second horizontal coordinate of point C in the middle can be calculated according to formula 8, which is

[0108] When calculating the third point ( Figure 4 When the third longitudinal coordinate of point A in the middle is calculated, it can be calculated according to formula 9, which is

[0109] When calculating the third point ( Figure 4 When the third horizontal coordinate of point A in the middle is calculated, it can be calculated according to formula 10. Formula 10 is

[0110] When calculating the third point ( Figure 4 When the fourth longitudinal coordinate of point D in the middle is calculated, it can be calculated according to formula 11, which is

[0111] When calculating the third point ( Figure 4 When the fourth horizontal coordinate of point D in the middle is calculated, it can be calculated according to formula 12, which is

[0112] In the above formulas 5 to 12, B lgt is the first longitudinal coordinate of the first point relative to the origin, B lat is the first horizontal coordinate of the first point relative to the origin, C lgt is the second longitudinal coordinate of the point relative to the origin, C lat is the second horizontal coordinate of the second point relative to the origin, A lgt is the third longitudinal coordinate of the third point relative to the origin, A lat is the third horizontal coordinate of the third point relative to the origin, D lgtis the fourth longitudinal coordinate of the fourth point relative to the origin, D lat obs_pos is the fourth horizontal coordinate of the fourth point relative to the origin of the coordinate system. lat is the first horizontal distance, obs width is the width of the risk target, obs_length is the length of the risk target, obs_pos lgt is the first longitudinal distance.

[0113] Step S220, determining a second relative coordinate of the corresponding target radar relative to the coordinate origin.

[0114] In this step, only the relative coordinates of the target radar that can sense the target object relative to the coordinate origin are calculated. If both target radars can sense the target object, one of them can be selected for calculation.

[0115] In some embodiments, the vehicle can be located according to the longitudinal coordinate of the real-time position of the vehicle, the wheelbase of the vehicle calibrated by the corresponding target radar, the heading angle of the vehicle, the width of the vehicle calibrated by the target radar, and the Determine the longitudinal coordinates of the target radar relative to the coordinate origin of the corresponding radar; at the same time, according to the lateral coordinates of the real-time position of the vehicle, the wheelbase of the vehicle calibrated by the target radar, the heading angle of the vehicle, and the width of the vehicle calibrated by the target radar Determine the radar transverse coordinate of the corresponding target radar relative to the coordinate origin; finally form a second relative coordinate according to the radar longitudinal coordinate and the radar transverse coordinate.

[0116] When calculating the radar longitudinal coordinates of the corresponding target radar relative to the coordinate origin, the calculation can be performed according to Formula 13, which is:

[0117] X LD =drinfo_dr_x+B_LD×cos(Veh)-B_C_LD×sin(Veh).

[0118] When calculating the radar lateral coordinates of the corresponding radar relative to the coordinate origin, the calculation can be performed according to Formula 14, which is:

[0119] Y LD =drinfo_dr_y+B_LD×sin(Veh)-B_C_LD×cos(Veh).

[0120] In formula 13 and formula 14, X LD is the radar longitudinal coordinate corresponding to the radar relative to the coordinate origin, Y LDCorresponding to the radar longitudinal coordinates relative to the origin of the coordinate system, drinfo_dr_x is the longitudinal coordinate of the real-time position of the vehicle (the real-time longitudinal coordinate of the center point of the rear suspension of the vehicle), drinfo_dr_y is the lateral coordinate of the real-time position of the vehicle (the real-time lateral coordinate of the center point of the rear suspension of the vehicle), B_LD is the wheelbase of the vehicle calibrated by the radar, Veh is the heading angle of the vehicle, and B_C_LD is the width of the vehicle calibrated by the radar.

[0121] It should be noted that each second target object sensed by the radar will also save the corresponding target object ID.

[0122] Step S230, determining whether the second target and the risk target are the same target according to the first relative coordinates, the second relative coordinates and the position coordinates of the second target returned by the corresponding target radar.

[0123] In some embodiments, based on the position coordinates of the first point, the second point, the third point, the fourth point and the second relative coordinates of the second target object returned by the corresponding target radar, the third relative coordinates of the first point, the second point, the third point and the fourth point of the second target object relative to the coordinate origin are obtained; the first relative coordinates and the third relative coordinates are compared, and if the difference between the corresponding points is within a preset range, it is determined that the second target object and the risk target are the same target object.

[0124] Among them, the position coordinates include longitudinal coordinates and transverse coordinates. It can be understood that when determining the third relative coordinate, the longitudinal coordinates and transverse coordinates of the first point of the second target object returned by the corresponding target radar (the corresponding target radar refers to the radar when calculating the second relative coordinate) are first obtained, the longitudinal coordinates and transverse coordinates of the second point, the longitudinal coordinates and transverse coordinates of the third point, and the longitudinal coordinates and transverse coordinates of the fourth point. In addition, the radar longitudinal coordinates and radar transverse coordinates of the corresponding target radar have been calculated in the above steps. The longitudinal coordinates of the first point, the second point, the third point, and the fourth point of the second target object perceived by the target radar are added to the radar longitudinal coordinates of the corresponding target radar, and the longitudinal coordinates of the first point, the second point, the third point, and the fourth point of the second target object relative to the coordinate origin can be obtained; similarly, the transverse coordinates of the first point, the second point, the third point, and the fourth point of the second target object perceived by the radar are added to the radar transverse coordinates of the corresponding radar, and the transverse coordinates of the first point, the second point, the third point, and the fourth point of the second target object relative to the coordinate origin can be obtained. After obtaining the horizontal coordinates of the first point, the second point, the third point and the fourth point of the second target object relative to the coordinate origin, and the vertical coordinates of the first point, the second point, the third point and the fourth point of the second target object relative to the coordinate origin, the third relative coordinates of the first point, the second point, the third point and the fourth point of the second target object relative to the coordinate origin are obtained.

[0125] After obtaining the first relative coordinates of the risk target and the third relative coordinates of the second target perceived by the radar, the relative coordinates of the first, second, third and fourth points of the risk target are compared with the relative coordinates of the first, second, third and fourth points corresponding to the second target to see whether the difference is within the preset range. If so, it means that the second target and the corresponding risk target are the same target, that is, the risk target is not lost. If the risk target is lost, the process ends.

[0126] Among them, if the risk target is not lost, the ID of the target object saved by the visual perception device can be fused with the target object ID saved by the radar, so as to avoid the loss of the target object during the vehicle turning process and the problem of retiming the target existence cycle.

[0127] If it is determined in the above steps that the risk target is not lost, step S300 is executed. When the vehicle continues to move, if the visual perception device cannot perceive the risk target and any of the target radars can still perceive the risk target, it is determined whether to trigger emergency braking according to the preset rules.

[0128] When the visual perception device cannot perceive the risk target, but the first radar or the second radar can still perceive the risk target, that is, the vehicle has reached Figure 1 The F' position shown in the figure, the risk target has walked to point F. At this time, the ego vehicle and the risk target are relatively close. In this case, the lateral position of the ego vehicle and the risk target at the second prediction time can be predicted again to determine whether there is a collision risk. If there is a collision risk, the historical data is used to determine whether emergency braking needs to be triggered. Since the ego vehicle and the risk target are already relatively close at this time, the first prediction time can be set to a maximum of 1 second, which can calculate the lateral position of the ego vehicle and the lateral position of the risk target at multiple prediction times in 1 second.

[0129] like Figure 7 As shown, judging whether emergency braking is triggered according to a preset rule includes steps S310 to S340:

[0130] Step S310: Obtain a third lateral position of the vehicle relative to the current position at a second prediction time according to the current third lateral velocity and third lateral acceleration of the vehicle.

[0131] When calculating the third lateral position, it can be calculated according to the above formula 2, which will not be described in detail here.

[0132] Step S320, obtaining a fourth lateral position of the risk target relative to the current position of the vehicle at the second prediction time according to the current fourth lateral velocity and fourth lateral acceleration of the risk target acquired by the corresponding target radar.

[0133] The current lateral position can be obtained according to the target radar. When the fourth lateral position is specifically calculated, it can be calculated according to Formula 4, which will not be described in detail here.

[0134] Step S330: determining whether there is a collision risk according to the third lateral position and the fourth lateral position.

[0135] In this step, as in S150, at any second prediction time, if the vehicle is turning right, if ped_obs_pos_lgt-ped_pos_lgt≤0, and ped_obs_pos_lat-ped_pos_lat≥0, it means that the vehicle has a collision risk with the risk target. If the vehicle is turning left, if ped_obs_pos_lgt-ped_pos_lgt≤0, and ped_obs_pos_lat-ped_pos_lat≤0, it means that the vehicle has a collision risk with the risk target.

[0136] If it is determined in step S330 that there is no collision risk between the vehicle and the risk target, the process ends. If it is determined in step S330 that there is a collision risk between the vehicle and the risk target, step S340 is executed to determine whether to trigger emergency braking based on the vehicle speed and the distance from the risk target to the vehicle returned by the corresponding target radar.

[0137] In this embodiment, the corresponding relationship between the distance of the risk target from the vehicle and the speed of the vehicle returned by the target radar under the working condition of step S300 is pre-stored, and the corresponding relationship is shown in the following table:

[0138] Vehicle speed (km / h) Radar return distance (m) Is it triggered? 10 <0.8 trigger 20 <1.2 trigger 30 <1.4 trigger

[0139] It can be understood that when the current speed of the vehicle is 10km / h, if the distance between the risk target returned by the target radar and the vehicle is less than 0.8m, emergency braking will be directly triggered; when the current speed of the vehicle is 20km / h, if the distance between the risk target returned by the target radar and the vehicle is less than 1.2m, emergency braking will be directly triggered; when the current speed of the vehicle is 30km / h, if the distance between the risk target returned by the target radar and the vehicle is less than 1.4m, emergency braking will be directly triggered. It can be understood that the correspondence between the distance between the risk target returned by the radar and the vehicle speed in the above table is only exemplary, and the specific correspondence can be set according to historical data, and no specific limitation is made here.

[0140] In the present application, when the ego vehicle needs to turn, the risk target in the target object is first determined based on the movement state of the ego vehicle and the target object. After the risk target is determined, since the ego vehicle and the risk target may continue to move, the risk target may be lost during the walking process. Therefore, in the present embodiment, when both the ego vehicle and the radar can perceive the target object, the position of the risk target perceived by the ego vehicle and the position of the target perceived by the radar are used to determine whether the target object perceived by the ego vehicle and the radar are the same. If so, it means that the risk target is not lost. Then, when the ego vehicle and the target object continue to move, when the visual perception device cannot perceive the risk target but the target radar can still perceive the risk target, it means that the front of the ego vehicle has exceeded the risk target. At this time, it is determined whether to trigger emergency braking according to the preset rules to avoid a collision between the ego vehicle and the target object.

[0141] Figure 8 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:

[0142] The risk target determination module 100 is used to determine whether the first target object is a risk target based on the motion state of the vehicle and the motion state of the first target object in the lane adjacent to the turning side obtained by the visual perception device when the vehicle needs to turn.

[0143] The judgment module 200 is used to judge whether the second target object sensed by the corresponding target radar and the risk target are the same target object when any target radar senses the second target object in the lane adjacent to the turning side; wherein the target radars are two radars set at the vehicle corner position on the turning side of the vehicle.

[0144] The emergency braking determination module 300 is used to determine whether to trigger emergency braking according to preset rules if, during the vehicle's continued movement, the visual perception device cannot perceive the risk target and any of the target radars can still perceive the risk target.

[0145] 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.

[0146] The present application also provides a vehicle. Exemplarily, the vehicle includes a processor and a memory, wherein the memory stores a computer program, and the processor runs the computer program to enable the vehicle to execute the functions of each module in the above-mentioned vehicle collision avoidance method or the above-mentioned vehicle collision avoidance device.

[0147] 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.

[0148] 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.

[0149] The present application also provides a computer-readable storage medium for storing the computer program used in the above-mentioned vehicle. 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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 vehicle needs to turn, judging whether the first target object is a risk target according to the motion state of the vehicle and the motion state of the first target object in the lane adjacent to the turning side acquired by the visual perception device; If so, when any target radar senses a second target in the lane adjacent to the turning side, it is determined whether the second target sensed by the corresponding target radar and the risk target are the same target; wherein the target radars are two radars arranged at the vehicle corner position on the turning side of the vehicle; If so, when the vehicle continues to move, if the visual perception device cannot perceive the risk target and any one of the target radars can still perceive the risk target, it is determined whether to trigger emergency braking according to preset rules.

2. The vehicle collision avoidance method according to claim 1, characterized in that: Judging whether a first target object is a risk target according to the motion state of the vehicle and the motion state of a first target object in a lane adjacent to the turning side acquired by a visual perception device includes: Acquire a first longitudinal position of the vehicle at a first prediction time according to a first longitudinal velocity and a first longitudinal acceleration of the vehicle; Acquire a first lateral position of the vehicle at the first prediction time according to a first lateral velocity and a first lateral acceleration of the vehicle; Acquire a second longitudinal position of the first target object at the first predicted time according to the second longitudinal velocity and the second longitudinal acceleration of the first target object and the current longitudinal position of the first target object; Acquire a second lateral position of the first target object at the first predicted time according to the second lateral velocity and the second lateral acceleration of the first target object and the current lateral position of the first target object; Whether the first target object is the risk target is determined according to the first longitudinal position, the second longitudinal position, the first lateral position, the second lateral position, and the turning direction of the vehicle.

3. The vehicle collision avoidance method according to claim 1, characterized in that: The determining whether the second target object sensed by the target radar and the risk target are the same target object includes: Determining a first relative coordinate of the risk target relative to a coordinate origin; Determine a second relative coordinate corresponding to the target radar relative to the coordinate origin; Whether the second target object and the risk target are the same target object is determined according to the first relative coordinates, the second relative coordinates, and the position coordinates of the second target object returned by the corresponding target radar.

4. The vehicle collision avoidance method according to claim 3, characterized in that: The determining of the first relative coordinate of the risk target relative to the coordinate origin includes: Determine a first longitudinal coordinate and a second longitudinal coordinate according to the first longitudinal distance, the width of the risk target and the target angle; Determine a first transverse coordinate and a second transverse coordinate according to the first transverse distance, the width of the risk target and the target angle; Determine a third longitudinal coordinate and a fourth longitudinal coordinate according to the first longitudinal distance, the width of the risk target, the target angle, and the length of the risk target; Determining a third transverse coordinate and a fourth transverse coordinate according to the first transverse distance, the width of the risk target, the target angle, and the length of the risk target; The first longitudinal coordinate and the first transverse coordinate are the first relative coordinates corresponding to the first point; the second longitudinal coordinate and the second transverse coordinate are the first relative coordinates corresponding to the second point; the third longitudinal coordinate and the third transverse coordinate are the first relative coordinates corresponding to the third point; the fourth longitudinal coordinate and the fourth transverse coordinate are the first relative coordinates corresponding to the fourth point; The first point and the second point are points at the tail of the risk target frame close to and away from the corresponding points of the vehicle; the third point and the fourth point are points at the head of the risk target frame close to and away from the corresponding points of the vehicle; the risk target frame is a rectangular frame composed of the width and length of the risk target; The first longitudinal distance is the longitudinal distance between the center point of the tail of the risk target and the origin of the vehicle coordinate system; the first lateral distance is the lateral distance between the center point of the tail of the risk target and the origin of the vehicle coordinate system; the target angle is the angle formed by a line in the longitudinal direction of the vehicle and a line in the longitudinal direction of the risk target.

5. The vehicle collision avoidance method according to claim 4, characterized in that: The determining of the second relative coordinates corresponding to the target radar relative to the coordinate origin includes: According to the longitudinal coordinate of the real-time position of the vehicle, the wheelbase of the vehicle calibrated by the target radar, the heading angle of the vehicle, and the width of the vehicle calibrated by the target radar, Determine the radar longitudinal coordinate of the corresponding radar relative to the coordinate origin; According to the lateral coordinates of the real-time position of the vehicle, the wheelbase of the vehicle calibrated by the target radar, the heading angle of the vehicle, and the width of the vehicle calibrated by the target radar, Determine the radar lateral coordinates of the corresponding radar relative to the coordinate origin; The radar longitudinal coordinate and the radar transverse coordinate constitute the second relative coordinate.

6. The vehicle collision avoidance method according to claim 5, characterized in that: The determining whether the second target and the risk target are the same target according to the first relative coordinates, the second relative coordinates and the position coordinates of the second target returned by the corresponding radar includes: Acquire third relative coordinates of the first point, the second point, the third point, and the fourth point of the second target object relative to the coordinate origin according to the position coordinates of the first point, the second point, the third point, the fourth point, and the second relative coordinates returned by the corresponding radar; The first relative coordinate and the third relative coordinate are compared, and if the difference between the corresponding points is within a preset range, it is determined that the second target object and the risk target are the same target object.

7. The vehicle collision avoidance method according to claim 1, characterized in that: The determining whether to trigger emergency braking according to a preset rule includes: Obtaining a third lateral position of the vehicle relative to the current position at a second prediction time according to the current third lateral speed and third lateral acceleration of the vehicle; Obtaining a fourth lateral position of the risk target relative to the current position of the vehicle at the second prediction time according to a current fourth lateral speed and a fourth lateral acceleration of the risk target acquired by the corresponding target radar; determining whether there is a collision risk according to the third lateral position and the fourth lateral position; If yes, whether to trigger emergency braking is determined according to the vehicle speed and the distance between the risk target and the vehicle returned by the target radar.

8. A vehicle collision avoidance device, characterized in that: include: A risk target determination module, used for determining whether the first target object is a risk target according to the motion state of the vehicle and the motion state of the first target object in the lane adjacent to the turning side acquired by the visual perception device when the vehicle needs to turn. A judgment module, for judging whether, when any target radar senses a second target in the lane adjacent to the turning side, the second target sensed by the corresponding target radar and the risk target are the same target; wherein the target radars are two radars arranged at the vehicle corner position on the turning side of the vehicle; The emergency braking determination module is used to determine whether to trigger emergency braking according to preset rules if, during the vehicle's continued movement, the visual perception device cannot perceive the risk target and any one of the target radars can still perceive the risk target.

9. A vehicle, characterized in that: The vehicle 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 7.

10. A computer-readable storage medium, characterized in that: The computer program is stored therein, and when the computer program is executed on a processor, the vehicle collision avoidance method according to any one of claims 1 to 7 is implemented.

Images