Vehicle collision avoidance control method, device, equipment, medium and program product

Abstract

The invention relates to a vehicle collision avoidance control method, device and equipment, a medium and a program product. The method comprises the steps of obtaining motion information of a vehicle and a target object around the vehicle to determine a collision position, determining a plurality of collision avoidance tracks according to the collision position and the maximum transverse avoidance distance of the vehicle, and establishing a cost function based on an offset parameter, the maximum transverse avoidance distance and the transverse acceleration of the current vehicle running according to the collision avoidance tracks, and a proper collision avoidance track can be selected to control the vehicle to realize avoidance. According to the collision avoidance track selected through the cost function established by the method, the safety of the collision avoidance terminal point and the transverse acceleration change of the vehicle in the collision avoidance process can be considered, the vehicle body stability is improved while the collision avoidance safety of the vehicle is guaranteed, and therefore the overall collision avoidance safety of the vehicle can be improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control, and in particular to a vehicle collision avoidance control method, device, equipment, medium and program product. Background Art

[0002] With the development of the automobile industry, the assisted driving function of automobiles is becoming more and more powerful. When there is a risk of collision between the vehicle and pedestrians or other vehicles, the assisted driving can avoid the collision by emergency braking or steering to avoid the collision.

[0003] At present, the vehicle's steering collision avoidance control strategy is relatively simple, and most decisions are made based on the driver's steering intention and hand torque. If safe avoidance is to be achieved, the driver still needs to intervene and control. If the driver operates improperly, avoidance failure or vehicle rollover may occur, and safety needs to be improved. Summary of the invention

[0004] One of the purposes of the present invention is to provide a vehicle collision avoidance control method, device, equipment, medium and program product to solve the problem of insufficient safety of the vehicle collision avoidance process.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A vehicle collision avoidance control method, comprising:

[0007] Acquire the first motion information of the current vehicle and the second motion information of the target object around the current vehicle

[0008] determining a collision position according to the first motion information and the second motion information;

[0009] Determine a plurality of collision avoidance endpoints and a collision avoidance trajectory corresponding to each collision avoidance endpoint according to the collision position and a preset maximum lateral avoidance distance;

[0010] A cost function is established based on an offset parameter, the maximum lateral avoidance distance, and a lateral acceleration corresponding to the collision avoidance trajectory, and a target collision avoidance trajectory is selected so that the value of the cost function satisfies a preset condition to control the current vehicle to avoid the collision. The offset parameter represents the lateral offset of the current vehicle corresponding to the collision avoidance endpoint.

[0011] Further, a plurality of collision avoidance endpoints are determined according to the collision position and a preset maximum lateral avoidance distance, including:

[0012] determining a lateral overlap amount at the collision location based on a boundary of the current vehicle and a boundary of the target object;

[0013] determining a minimum offset according to the collision position and the lateral overlap amount;

[0014] Determine a maximum offset according to the minimum offset and the maximum lateral avoidance distance;

[0015] The collision position is offset according to the minimum offset and the maximum offset to obtain a plurality of collision avoidance endpoints.

[0016] Further, a cost function is established based on the offset parameter, the maximum lateral avoidance distance and the lateral acceleration corresponding to the collision avoidance trajectory, including:

[0017] determining a collision time according to the first motion information and the collision position;

[0018] Calculating the lateral uniform acceleration corresponding to the collision avoidance trajectory according to the collision time and the collision avoidance endpoint;

[0019] Selecting a collision avoidance trajectory whose lateral uniform acceleration is less than a preset acceleration threshold for longitudinal sampling, and determining the lateral instantaneous acceleration of the collision avoidance trajectory according to the sampling result;

[0020] A cost function is established based on the offset parameter, the maximum lateral avoidance distance and the lateral instantaneous acceleration.

[0021] Further, selecting a target collision avoidance trajectory that makes the value of the cost function meet a preset condition includes:

[0022] Traverse the values ​​of the cost function corresponding to each collision avoidance trajectory, and select the collision avoidance trajectory corresponding to the minimum value as the target collision avoidance trajectory.

[0023] Furthermore, the value of the cost function is obtained as follows:

[0024] For any collision avoidance trajectory whose lateral uniform acceleration is less than a preset acceleration threshold, selecting a number of sampling points in the collision avoidance trajectory according to a preset longitudinal sampling step size;

[0025] The cumulative cost value of the lateral instantaneous acceleration corresponding to the selected sampling point is calculated as the value of the cost function.

[0026] Furthermore, the value of the cost function corresponding to the collision avoidance trajectory where the sampling point is located is set to a preset target value.

[0027] A vehicle collision avoidance control device, comprising:

[0028] An acquisition module, used to acquire first motion information of a current vehicle and second motion information of a target object around the current vehicle;

[0029] a collision determination module, configured to determine a collision position according to the first motion information and the second motion information;

[0030] A trajectory determination module, used to determine a plurality of collision avoidance endpoints and a collision avoidance trajectory corresponding to each collision avoidance endpoint according to the collision position and a preset maximum lateral avoidance distance;

[0031] A collision avoidance processing module is used to establish a cost function based on an offset parameter, the maximum lateral avoidance distance and the lateral acceleration corresponding to the collision avoidance trajectory, and select a target collision avoidance trajectory that makes the value of the cost function meet a preset condition to control the current vehicle to avoid, wherein the offset parameter represents the lateral offset of the current vehicle corresponding to the collision avoidance endpoint.

[0032] An electronic device comprises: a processor, and a memory communicatively connected to the processor;

[0033] The memory stores computer-executable instructions;

[0034] The processor executes the computer-executable instructions stored in the memory to implement the vehicle collision avoidance control method as described in any one of the above items.

[0035] A computer-readable storage medium comprises: the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to implement the vehicle collision avoidance control method as described in any one of the above when executed by a processor.

[0036] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the vehicle collision avoidance control method as described in any one of the above items is implemented.

[0037] The beneficial effects of the present invention are as follows: by establishing a cost function related to the collision avoidance end point and the lateral acceleration to select a collision avoidance trajectory, the safety of the collision avoidance end point and the change in the lateral acceleration of the vehicle during the collision avoidance process can be taken into account, so that the vehicle can improve the body stability while ensuring the collision avoidance safety, thereby improving the overall safety of the vehicle in collision avoidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A schematic flow chart of a vehicle collision avoidance control method provided by an exemplary embodiment of the present invention;

[0039] Figure 2 A schematic diagram of a collision avoidance scenario provided for an exemplary embodiment of the present invention;

[0040] Figure 3 A schematic diagram of a process for establishing a cost function provided by an exemplary embodiment of the present invention;

[0041] Figure 4 A schematic diagram of a process for obtaining a cost function value provided by an exemplary embodiment of the present invention;

[0042] Figure 5A schematic structural diagram of a vehicle collision avoidance control device provided by an exemplary embodiment of the present invention;

[0043] Figure 6 A schematic structural diagram of an electronic device provided by an exemplary embodiment of the present invention.

[0044] Through the above drawings, clear embodiments of the present invention have been shown, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0045] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0046] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0047] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0048] The terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, product or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of further restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For example, if the words first, second, etc. are used to indicate names, they do not indicate any particular order.

[0049] The Automatic Emergency Brake (AEB) system receives information such as the distance and speed of the vehicle in front, pedestrians or obstacles detected by sensors such as radar and cameras, and determines whether there is a risk of collision between the vehicle and the target in front under different relative speeds and relative positions. When there is a risk of collision, AEB will automatically send an alarm to the driver. Then, when the distance to the target in front is less than the safe distance and the driver does not brake in time, AEB will automatically trigger deceleration and request the vehicle's brake controller to decelerate as much as possible to avoid collision. However, when the vehicle is traveling at high speed, if a target such as a ghost suddenly appears in front and the longitudinal distance between the vehicle and the vehicle is significantly less than the latest trigger distance of AEB, it is generally difficult for AEB to brake to avoid collision.

[0050] In view of this, when the vehicle cannot avoid collision by emergency braking, if the driving space in the adjacent area of ​​the collision route meets the turning conditions, the vehicle can avoid the target ahead by turning to ensure driving safety. However, the inventors found that the current vehicle steering avoidance process requires obtaining the driver's steering intention and the hand torque applied to the steering wheel to make collision avoidance decisions. The planning effect of the collision avoidance trajectory is not good. When the end point of the collision avoidance trajectory is close to the target object, it may still cause scratches, etc. When the end point of the collision avoidance trajectory is far from the target object, the lateral acceleration of the vehicle will change too much and cause the vehicle body to be unstable. How to plan a safer collision avoidance trajectory is a major problem that has not yet been solved.

[0051] The inventor therefore thought that multiple collision avoidance trajectories could be determined based on the vehicle's own maximum avoidance distance and the actual location where a collision might occur, and a cost function could be established based on the acceleration of the collision avoidance trajectory and the lateral offset of the end point of the collision avoidance trajectory. A safer collision avoidance trajectory could be determined based on the cost function, taking into account the safety of the collision avoidance end point and the change in lateral acceleration of the vehicle during the collision avoidance process, so that the vehicle can improve body stability while ensuring collision avoidance safety, thereby improving the overall safety of the vehicle's collision avoidance.

[0052] Figure 1 FIG. 1 is a flow chart of a vehicle collision avoidance control method provided by an exemplary embodiment of the present invention. Figure 1 As shown, the method may include:

[0053] Step S101, obtaining first motion information of a current vehicle and second motion information of target objects around the current vehicle.

[0054] The first motion information may include information such as the position, speed, heading angle, and bounding box coordinates of the current vehicle, and the bounding box may represent the outline of the current vehicle. The target object may be an obstacle encountered by the current vehicle on its route, such as a pedestrian or other vehicle in front of the road where the current vehicle is located. The second motion information may include information such as the position, speed, heading angle, and bounding box coordinates of the target object.

[0055] Specifically, the vehicle's speed, position and other information can be collected through devices such as the current vehicle's speed sensor, and the movement speed, position and other information of target objects such as the vehicle in front can be collected through devices such as cameras and radars. It should be noted that the position of the current vehicle and the position of the target object can both be expressed as coordinates in a reference system established based on the current vehicle.

[0056] For example, the current vehicle can be taken as the coordinate origin, the direction parallel to the center of the rear axle of the current vehicle as the horizontal axis, and the direction perpendicular to the horizontal axis in the horizontal plane as the vertical axis. A coordinate system in the horizontal plane is established based on the coordinate origin, horizontal axis and vertical axis, and the position of the current vehicle and the target object are represented as coordinates in the coordinate system.

[0057] Step S102: determining a collision position according to the first motion information and the second motion information.

[0058] For example, according to the motion information of the current vehicle and the motion information of the target object, the trajectory algorithm such as the third-order Bezier curve can be combined to predict the current vehicle in T0~T n The motion trajectory within seconds; calculate the target T0~T in front with Δt as the step size n The motion information such as position, speed, heading angle, bounding box coordinates, etc. within seconds is calculated with a step size of Δt from T0 to T n-1 Traverse and calculate the current vehicle at each sampling time point T i The position, speed, heading angle, bounding box coordinates and other motion information of the current vehicle and the target object in front of it correspond to the time point T i The motion information at the moment is used to calculate the earliest time T when the current vehicle bounding box collides with the bounding box of the target object through the collision detection algorithm. c , and use T c Query the coordinates of the collision corner point of the current vehicle at this moment (y c , x c ) as the collision position. T0 can be the current time, T n Can be any preset value, y c and x c They respectively represent the horizontal and vertical coordinates of the collision position in the coordinate system.

[0059] Step S103, determining a plurality of collision avoidance endpoints and a collision avoidance trajectory corresponding to each collision avoidance endpoint according to the collision position and a preset maximum lateral avoidance distance.

[0060] The maximum lateral avoidance distance may be the maximum lateral avoidance distance allowed by the system performance of the current vehicle.

[0061] Specifically, in order to take into account the vehicle's driving stability while achieving collision avoidance, the lateral offset range required for collision avoidance can be solved according to the two ideas of achieving collision avoidance with the minimum offset and achieving collision avoidance with the maximum lateral avoidance distance defined by the vehicle system, and the collision avoidance end point can be determined accordingly.

[0062] For example, refer to Figure 2 As shown, first, we can calculate the collision position when the collision occurs (T c The horizontal overlap y between the current vehicle bounding box and the front target object bounding box at time cover , we can set the collision avoidance end point coordinates as (y end , x end ). Among them, the longitudinal coordinate of the collision avoidance end point can remain unchanged with the longitudinal coordinate of the collision point, that is, x end =x c .

[0063] If the idea of ​​collision avoidance is realized by the minimum offset, such as Figure 2 As shown, you can set y end =y c +|y cover |, in order to achieve collision avoidance. Optionally, considering the possible deviation of the current vehicle when performing lateral ranging through the perception system, y can be set end =y c +|y cover |+y safe , where y safe is a calibrable lateral safety margin. By setting this lateral safety margin, it can be ensured that the vehicle can avoid collision even when the perception system's lateral distance measurement of the target is too small.

[0064] If the maximum lateral avoidance distance defined by the vehicle system is used to achieve collision avoidance, the longitudinal coordinate y of the collision avoidance end point can be set. end =y c +|y cover |+y MAX , to achieve collision avoidance. Among them, y MAX It is the maximum lateral avoidance distance allowed by the system.

[0065] Optionally, considering the above two ideas, let the longitudinal coordinate x of the collision avoidance end point be end =x c , and the horizontal coordinate y endThe value range is set to [y c +|y cover |+y safe ,y c +|y cover |+y MAX ], multiple collision avoidance endpoints can be obtained by selecting the horizontal coordinates in the value range. After the collision avoidance endpoint is obtained, the collision avoidance trajectory corresponding to the collision avoidance endpoint can be generated by the collision avoidance algorithm.

[0066] Step S104, establishing a cost function based on the offset parameter, the maximum lateral avoidance distance and the lateral acceleration corresponding to the collision avoidance trajectory, and selecting a target collision avoidance trajectory that makes the value of the cost function meet a preset condition to control the current vehicle to avoid.

[0067] The offset parameter represents the lateral offset of the current vehicle corresponding to the collision avoidance endpoint.

[0068] Specifically, the current vehicle performs collision avoidance from time T0 until time T c In the process of completing the collision avoidance at any moment, the lateral coordinate value of the collision avoidance endpoint can represent the lateral offset of the current vehicle during the collision avoidance process. The cost function can be established with the lateral offset, the maximum lateral avoidance distance, the maximum lateral acceleration and the lateral acceleration of the current vehicle during the collision avoidance process. The cost function can be used to solve the collision avoidance results and collision avoidance stability during the vehicle collision avoidance process. By setting constraints on the value of the cost function, a collision avoidance trajectory with higher stability can be selected, so that the current vehicle can be controlled to achieve collision avoidance according to the selected collision avoidance trajectory.

[0069] In the above embodiment, the collision position can be determined by acquiring the motion information of the vehicle and the target objects around the vehicle, and multiple collision avoidance trajectories can be determined according to the collision position and the maximum lateral avoidance distance of the vehicle. Then, a cost function is established based on the offset parameter, the maximum lateral avoidance distance and the lateral acceleration of the current vehicle traveling according to the collision avoidance trajectory, and a suitable collision avoidance trajectory can be selected to control the vehicle to achieve avoidance. The collision avoidance trajectory selected by the cost function established by the method of the present invention can take into account the safety of the collision avoidance endpoint and the change in the lateral acceleration of the vehicle during the collision avoidance process, so that the vehicle can improve the stability of the vehicle body while ensuring collision avoidance safety, thereby improving the overall safety of vehicle collision avoidance.

[0070] In one embodiment, multiple collision avoidance endpoints are determined according to the collision position and a preset maximum lateral avoidance distance, including:

[0071] The minimum offset is determined according to the collision position and the lateral overlap; the maximum offset is determined according to the minimum offset and the maximum lateral avoidance distance; the collision position is offset according to the minimum offset and the maximum offset to obtain multiple collision avoidance end points.

[0072] For example, refer to Figure 2 , the minimum offset can be the longitudinal coordinate value y of the collision point c The horizontal overlap y cover The maximum offset can be the sum of the minimum offset and the maximum avoidance distance. The numerical range between the minimum offset and the maximum offset is the lateral offset range that the current vehicle needs to consider when avoiding collisions. By taking values ​​within this range and performing lateral offsets based on the collision position, the corresponding collision avoidance endpoint can be obtained. Multiple values ​​can be taken, and accordingly, multiple collision avoidance endpoints can be obtained.

[0073] In one embodiment, Figure 3 As shown, a cost function is established based on the offset parameter, the maximum lateral avoidance distance and the lateral acceleration corresponding to the collision avoidance trajectory, including:

[0074] Step S301: determining the collision time according to the first motion information and the collision position.

[0075] Specifically, the first motion information may include the current vehicle's driving speed. According to the collision position of the current vehicle on the driving trajectory, combined with the driving speed, the time required for the current vehicle to travel to the position can be predicted.

[0076] Step S302, calculating the lateral uniform acceleration corresponding to the collision avoidance trajectory according to the collision time and the collision avoidance endpoint.

[0077] In order to ensure the stability of the current vehicle during collision avoidance steering, the lateral acceleration a of the current vehicle during steering is required. safe , a safe It can be the maximum lateral acceleration allowed to maintain the stability of the current vehicle under different speed ranges. To meet the requirements of steering stability, it can be assumed that the vehicle can turn in two ways: lateral uniform acceleration and variable acceleration, and by making the uniform acceleration of the vehicle a avg and the changing instantaneous acceleration a t All less than a safe The inventor found that when the instantaneous acceleration a t safe When a avg safe Therefore, the total lateral displacement of the current vehicle during the collision avoidance process can be determined based on the lateral coordinate value of the collision avoidance end point, and the ratio of the total displacement to the collision event can be calculated to obtain the lateral uniform acceleration of the current vehicle.

[0078] Step S303 , selecting a collision avoidance trajectory whose lateral uniform acceleration is less than a preset acceleration threshold for longitudinal sampling, and determining the lateral instantaneous acceleration of the collision avoidance trajectory according to the sampling result.

[0079] ​​​The acceleration threshold can be the maximum lateral acceleration a allowed to maintain the stability of the current vehicle at different speed ranges. safe .

[0080] Specifically, we can use the binary search to find the acceleration a avg safe The corresponding y end The value range is set N, and then the horizontal sampling interval Δy is set sample Divide the set N into equal parts to obtain avg safe The lateral coordinate of the collision avoidance endpoint In getting the collection After that, you can set the longitudinal sampling step length Δx sample , for the collection The collision avoidance trajectory corresponding to any lateral coordinate in is sampled using the longitudinal sampling step to obtain multiple sampling points, and the lateral acceleration at the adjacent longitudinal sampling points on the collision avoidance trajectory is approximately equivalent to the lateral instantaneous acceleration. A collision avoidance trajectory is determined, and there are two adjacent longitudinal sampling points A and B on the trajectory. By obtaining the difference in lateral driving speeds corresponding to sampling point A and sampling point B, and the time required for the current vehicle to travel from sampling point A to sampling point B according to the collision avoidance trajectory, the ratio of the difference to the time is calculated and the ratio is approximated as a lateral instantaneous acceleration in the trajectory.

[0081] Step S304: establishing a cost function based on the offset parameter, the maximum lateral avoidance distance and the lateral instantaneous acceleration.

[0082] Exemplarily, the cost function can be expressed as follows:

[0083]

[0084] The cost function can be expressed as And the formula that characterizes the stability of the vehicle Weighted composition. In the cost function |a safe | is the maximum allowable acceleration of the vehicle during the emergency steering process required by functional safety, which can characterize the stability of the vehicle during the emergency steering process. If the lateral acceleration of the vehicle is a y The closer the absolute value of (i) is to |a safe |, the lower the stability of the ego vehicle. K is the weight coefficient of the cost function for safety and stability. In this example, K can be set to 0.7, so that the ability of the ego vehicle to avoid collisions safely is given more weight while considering the emergency steering stability of the ego vehicle. end (i) is based on the preset step size, from [y c +|y cover ​​|+y safe ,y c +|y cover |+y MAX ], the step length can be the horizontal sampling interval Δy sample , the step length can be 0.2 meters. y (i) is based on y end (i) is the lateral acceleration of the vehicle at the lateral coordinate of the collision avoidance endpoint, a y (i) The calculation can be expressed as the following formula (1):

[0085] a y (i) = 2 × (y end (i)-v y (i)×T c (i)) / T c (i) 2 (1)

[0086] Where T c (i) is y end (i) is the predicted time of collision between the vehicle and the vehicle in front at the end point of lateral collision avoidance. This cost function can be used to solve the collision avoidance results and collision avoidance stability of the vehicle during the collision avoidance process. By selecting the minimum cost function value calculated at each collision avoidance end point as the optimal collision avoidance trajectory that is both safe and stable, the current vehicle can be controlled to achieve collision avoidance.

[0087] In one embodiment, selecting a target collision avoidance trajectory that makes the value of the cost function satisfy a preset condition includes:

[0088] Traverse the values ​​of the cost function corresponding to each collision avoidance trajectory, and select the collision avoidance trajectory corresponding to the minimum value as the target collision avoidance trajectory.

[0089] Specifically, through the above steps, we can get avg safe For the collision avoidance endpoint, for the collision avoidance trajectory corresponding to each collision avoidance endpoint, the value of the cost function can be calculated, and the collision avoidance trajectory when the value of the cost function is minimized is selected as the target collision avoidance trajectory.

[0090] In one embodiment, Figure 4 As shown, the value of the cost function is obtained by:

[0091] Step S401 : for any collision avoidance trajectory whose lateral uniform acceleration is less than a preset acceleration threshold, select a number of sampling points in the collision avoidance trajectory according to a preset longitudinal sampling step size.

[0092] Step S402 : calculating the cumulative cost value of the lateral instantaneous acceleration corresponding to the selected sampling point as the value of the cost function. ​

[0093] Specifically, in order to obtain a avg safe The lateral coordinate of the collision avoidance endpoint Then, we can use the polynomial in the following formula (2) with (y0, x0) as the starting point and (y end_n ,x0) is the end point for fitting.

[0094] y(x)=c0+c1(x-x0)+c2(x-x0) 2 +c3(x-x3) 3 +c4(x-x4) 4 +c5(x-x5) 5 (2)

[0095] In the above formula, y(x) can represent the longitudinal coordinate of the current vehicle on the track, x can represent the transverse coordinate on the track, c0~c5 are all polynomial coefficients. x0 is the longitudinal coordinate of the current vehicle at the current time T0, and the value can be set to 0.

[0096] After the vehicle completes the collision avoidance according to the collision avoidance trajectory, the body system can control the body to return to the center position. The lateral velocity, lateral acceleration and heading angle at the end point of the collision avoidance trajectory can be set to 0. Based on this, the following formula (3) can be obtained.

[0097]

[0098] According to formula (2), at the starting point of the collision avoidance trajectory (y0, x0), c0~c2 are related to the lateral position y0, slope tan(θ0), and lateral velocity v of the starting point of the trajectory. 0_lat and lateral acceleration a 0_lat There is the following formula (4):

[0099]

[0100] If the current vehicle is used as the origin of the coordinate system, the current vehicle heading direction is the longitudinal axis direction of the coordinate system, and the direction parallel to the rear axle is the transverse axis direction of the coordinate axis, then at (y0, x0), the heading angle θ0≈0. When θ0 is small, tan(θ0)≈θ0, so It can be approximated as the curvature here, thus obtaining the following formula (5).

[0101]

[0102] in, It can be obtained by differential approximation calculation, and formula (4) can be converted into the following formula (6).

[0103]

[0104] ​According to the above formula, the polynomial coefficients in formula (2) can be expressed as the following formula (7).

[0105]

[0106] Optionally, based on the above formula, for each item that satisfies a avg safe The collision avoidance trajectory with the condition in the form of a quintic polynomial is sampled longitudinally. For each collision avoidance trajectory, the lateral acceleration at the adjacent longitudinal sampling points is approximately considered to be equivalent to the instantaneous acceleration. The instantaneous acceleration cumulative cost on each collision avoidance trajectory is calculated along the trajectory from the end point of the collision avoidance, so that at the starting point of each collision avoidance trajectory, the acceleration cost generated by the trajectory during the collision avoidance process is obtained. The sum of the lateral acceleration costs that may be generated by each trajectory during the collision avoidance process is traversed, and the collision avoidance trajectory with the minimum cost is selected as the final target collision avoidance trajectory.

[0107] In one embodiment, the vehicle collision avoidance control method may further include:

[0108] If the lateral instantaneous acceleration corresponding to the sampling point is greater than or equal to the acceleration threshold, the value of the cost function corresponding to the collision avoidance trajectory where the sampling point is located is set to a preset target value.

[0109] For example, after longitudinal sampling of the collision avoidance trajectory, if the instantaneous lateral acceleration a corresponding to adjacent sampling points in the trajectory is t Greater than or equal to a safe , you can directly set the acceleration cost value of the trajectory to infinity.

[0110] In order to ensure the stability of the vehicle during collision avoidance, the instantaneous lateral acceleration a of the current vehicle is t Should be less than a safe If the lateral instantaneous acceleration obtained after longitudinal sampling of a collision avoidance trajectory is greater than or equal to this value, the cost of the collision avoidance trajectory can be directly set to infinity. In this way, the collision avoidance trajectory can be directly discarded, the amount of calculation can be reduced, and the efficiency of collision avoidance decision-making can be improved.

[0111] Figure 5 FIG. 1 is a schematic diagram of a vehicle collision avoidance control device provided by an exemplary embodiment of the present invention. Figure 5 As shown, the vehicle collision avoidance control device 500 may include:

[0112] The acquisition module 501 is used to acquire first motion information of the current vehicle and second motion information of target objects around the current vehicle.

[0113] The collision determination module 502 is configured to determine a collision position according to the first motion information and the second motion information.

[0114] ​The trajectory determination module 503 is used to determine a plurality of collision avoidance endpoints and a collision avoidance trajectory corresponding to each collision avoidance endpoint according to the collision position and a preset maximum lateral avoidance distance.

[0115] The collision avoidance processing module 504 is used to establish a cost function based on an offset parameter, the maximum lateral avoidance distance and the lateral acceleration corresponding to the collision avoidance trajectory, and select a target collision avoidance trajectory that makes the value of the cost function meet a preset condition to control the current vehicle to avoid. The offset parameter represents the lateral offset of the current vehicle corresponding to the collision avoidance endpoint.

[0116] In one embodiment, the trajectory determination module 503 may include:

[0117] The overlap determination unit may be configured to determine a lateral overlap amount at the collision position according to a boundary of the current vehicle and a boundary of the target object.

[0118] The minimum offset unit may be used to determine a minimum offset according to the collision position and the lateral overlap amount.

[0119] The maximum offset unit may be used to determine a maximum offset according to the minimum offset and the maximum lateral avoidance distance.

[0120] The endpoint determination unit may be configured to offset the collision position according to the minimum offset and the maximum offset to obtain a plurality of collision avoidance endpoints.

[0121] In one embodiment, the collision avoidance processing module 504 may include:

[0122] The time processing unit may be configured to determine a collision time according to the first motion information and the collision position.

[0123] The uniform acceleration unit can be used to calculate the lateral uniform acceleration corresponding to the collision avoidance trajectory according to the collision time and the collision avoidance endpoint.

[0124] The instantaneous acceleration unit can be used to select a collision avoidance trajectory whose lateral uniform acceleration is less than a preset acceleration threshold for longitudinal sampling, and determine the lateral instantaneous acceleration of the collision avoidance trajectory according to the sampling result.

[0125] The function establishing unit can be used to establish a cost function based on the offset parameter, the maximum lateral avoidance distance and the lateral instantaneous acceleration.

[0126] In one embodiment, the collision avoidance processing module 504 is further used to: traverse the values ​​of the cost function corresponding to each collision avoidance trajectory, and select the collision avoidance trajectory corresponding to the minimum value as the target collision avoidance trajectory.

[0127] In one embodiment, the vehicle collision avoidance control device 600 may further include:

[0128] The longitudinal sampling module can be used to select a number of sampling points in any collision avoidance trajectory whose lateral uniform acceleration is less than a preset acceleration threshold according to a preset longitudinal sampling step size.

[0129] The cost calculation module can be used to calculate the cumulative cost value of the lateral instantaneous acceleration corresponding to the selected sampling point as the value of the cost function.

[0130] In one embodiment, the vehicle collision avoidance control device 600 may further include:

[0131] The target setting module can be used to set the value of the cost function corresponding to the collision avoidance trajectory where the sampling point is located to a preset target value when the lateral instantaneous acceleration corresponding to the sampling point is greater than or equal to the acceleration threshold.

[0132] The vehicle collision avoidance control device provided in this embodiment is used to execute the technical solution in any of the aforementioned method embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0133] It should be understood that the above device embodiments are only illustrative, and the device of the present invention can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units, modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0134] In addition, unless otherwise specified, each functional unit / module in each embodiment of the present invention may be integrated into one unit / module, or each unit / module may exist physically separately, or two or more units / modules may be integrated together. The above-mentioned integrated unit / module may be implemented in the form of hardware or in the form of a software program module.

[0135] Figure 6 FIG. 1 is a schematic diagram of a structure of an electronic device provided by an exemplary embodiment of the present invention. Figure 6 As shown, the electronic device 60 includes:

[0136] Processor 61, memory 62, and communication interface 63;

[0137] The memory 62 is used to store executable instructions of the processor 61; the executable instructions may be computer-executable instructions;

[0138] The processor 61 is configured to execute the technical solution in any of the aforementioned method embodiments by executing the executable instructions.

[0139] Optionally, the memory 62 may be independent or integrated with the processor 61 .

[0140] Optionally, when the memory 62 is a device independent of the processor 61, the electronic device 60 may further include:

[0141] The bus 64 , the memory 62 and the communication interface 63 are connected to the processor 61 via the bus 64 and communicate with each other. The communication interface 63 is used to communicate with other devices.

[0142] Optionally, the communication interface 63 may be implemented by a transceiver. The communication interface is used to implement communication between the database access device and other devices (such as a client, a read-write library, and a read-only library). The memory may include a random access memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage.

[0143] The bus 64 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0144] The above-mentioned processor can be a general-purpose processor, including a central processing unit CPU, a network processor (NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0145] The electronic device is used to execute the technical solution in any of the aforementioned method embodiments, and its implementation principle and technical effect are similar and will not be repeated here.

[0146] An embodiment of the present invention further provides a readable storage medium, which may be a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the technical solution provided by any of the aforementioned method embodiments is implemented.

[0147] An embodiment of the present invention further provides a computer program product, including a computer program, which is used to implement the technical solution provided by any of the aforementioned method embodiments when executed by a processor.

[0148] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0149] In the above embodiments, the description of each embodiment has its own emphasis. For the part not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention is indicated by the following claims.

[0151] The above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A vehicle collision avoidance control method, characterized in that: include: Acquire first motion information of a current vehicle and second motion information of a target object around the current vehicle; determining a collision position according to the first motion information and the second motion information; Determine a plurality of collision avoidance endpoints and a collision avoidance trajectory corresponding to each collision avoidance endpoint according to the collision position and a preset maximum lateral avoidance distance; A cost function is established based on an offset parameter, the maximum lateral avoidance distance, and a lateral acceleration corresponding to the collision avoidance trajectory, and a target collision avoidance trajectory is selected so that the value of the cost function satisfies a preset condition to control the current vehicle to avoid the collision. The offset parameter represents the lateral offset of the current vehicle corresponding to the collision avoidance endpoint.

2. The vehicle collision avoidance control method according to claim 1, characterized in that: The determining of a plurality of collision avoidance endpoints according to the collision position and a preset maximum lateral avoidance distance includes: determining a lateral overlap amount at the collision location based on a boundary of the current vehicle and a boundary of the target object; determining a minimum offset according to the collision position and the lateral overlap amount; Determine a maximum offset according to the minimum offset and the maximum lateral avoidance distance; The collision position is offset according to the minimum offset and the maximum offset to obtain a plurality of collision avoidance endpoints.

3. The vehicle collision avoidance control method according to claim 1 or 2, characterized in that: The cost function is established based on the offset parameter, the maximum lateral avoidance distance and the lateral acceleration corresponding to the collision avoidance trajectory, including: determining a collision time according to the first motion information and the collision position; Calculating the lateral uniform acceleration corresponding to the collision avoidance trajectory according to the collision time and the collision avoidance endpoint; Selecting a collision avoidance trajectory whose lateral uniform acceleration is less than a preset acceleration threshold for longitudinal sampling, and determining the lateral instantaneous acceleration of the collision avoidance trajectory according to the sampling result; A cost function is established based on the offset parameter, the maximum lateral avoidance distance and the lateral instantaneous acceleration.

4. The vehicle collision avoidance control method according to claim 3, characterized in that: The step of selecting a target collision avoidance trajectory that makes the value of the cost function satisfy a preset condition includes: Traverse the values ​​of the cost function corresponding to each collision avoidance trajectory, and select the collision avoidance trajectory corresponding to the minimum value as the target collision avoidance trajectory.

5. The vehicle collision avoidance control method according to claim 4, characterized in that: The value of the cost function is obtained in the following way: For any collision avoidance trajectory whose lateral uniform acceleration is less than a preset acceleration threshold, selecting a number of sampling points in the collision avoidance trajectory according to a preset longitudinal sampling step size; The cumulative cost value of the lateral instantaneous acceleration corresponding to the selected sampling point is calculated as the value of the cost function.

6. The vehicle collision avoidance control method according to claim 5, characterized in that: Also includes: If the lateral instantaneous acceleration corresponding to the sampling point is greater than or equal to the acceleration threshold, the value of the cost function corresponding to the collision avoidance trajectory where the sampling point is located is set to a preset target value.

7. A vehicle collision avoidance control device, characterized in that: include: An acquisition module, used to acquire first motion information of a current vehicle and second motion information of a target object around the current vehicle; a collision determination module, configured to determine a collision position according to the first motion information and the second motion information; A trajectory determination module, used to determine a plurality of collision avoidance endpoints and a collision avoidance trajectory corresponding to each collision avoidance endpoint according to the collision position and a preset maximum lateral avoidance distance; A collision avoidance processing module is used to establish a cost function based on an offset parameter, the maximum lateral avoidance distance and the lateral acceleration corresponding to the collision avoidance trajectory, and select a target collision avoidance trajectory that makes the value of the cost function meet a preset condition to control the current vehicle to avoid, wherein the offset parameter represents the lateral offset of the current vehicle corresponding to the collision avoidance endpoint.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images