CN116968736A

CN116968736A - Target tracking vehicle selection method, device and storage medium

Info

Publication number: CN116968736A
Application number: CN202310871388.1A
Authority: CN
Inventors: 朱雨成; 查安飞; 严益超
Original assignee: Zhejiang Zero Run Technology Co Ltd
Current assignee: Zhejiang Zero Run Technology Co Ltd
Priority date: 2023-04-23
Filing date: 2023-04-23
Publication date: 2023-10-31
Also published as: CN116176581B; CN116176581A; CN117068158A

Abstract

The application discloses a target tracking vehicle selection method, equipment and a storage medium, wherein the method comprises the following steps: acquiring first motion data of a self-vehicle at the current moment, wherein the first motion data at least comprises the running speed of the self-vehicle at the current moment; determining the yaw rate of the self-vehicle based on the running speed, the low-speed calibration value and the high-speed calibration value of the self-vehicle in the first motion data, and determining a first curvature of the self-vehicle when the self-vehicle is currently running according to the ratio of the yaw rate to the running speed; predicting the running track of the own vehicle in a future preset time period based on at least the first curvature to obtain a first predicted track; the target detection area is determined based at least on the first predicted trajectory, and the first target tracking vehicle is determined based on the detection of the target detection area. By means of the method, accuracy of determining the target tracking vehicle can be improved, and particularly under a lane-line-free scene, the target tracking vehicle can be accurately determined.

Description

Target tracking vehicle selection method, device and storage medium

Technical Field

The application discloses a target tracking vehicle selection method, equipment and storage medium, and a divisional application of patent application with application number 202310439134.2, which are proposed by applicant in 2023, 04 and 23, and relate to the technical field of data processing, in particular to a target tracking vehicle selection method, equipment and storage medium.

Background

In recent years, an automatic driving assistance system has been rapidly developed, wherein the automatic driving assistance system needs to determine a target tracking vehicle to be tracked during use so that a host vehicle can track the target tracking vehicle for traveling, wherein the accurate determination of the target tracking vehicle directly affects the use safety of the automatic driving assistance system. Therefore, how to accurately determine a target tracking vehicle to be tracked by a host vehicle is important.

Disclosure of Invention

The application mainly solves the technical problem of providing a target tracking vehicle selection method, equipment and a storage medium, which can improve the accuracy of determining the target tracking vehicle.

In order to solve the technical problems, the application adopts a technical scheme that: there is provided a target tracking vehicle selection method, the method comprising: acquiring first motion data of a vehicle at the current moment; the first motion data at least comprises the running speed of the own vehicle at the current moment; determining a first curvature of the own vehicle when the own vehicle is currently running based on the first motion data, the low-speed calibration value and the high-speed calibration value; predicting the running track of the own vehicle in a future preset time period based on at least the first curvature to obtain a first predicted track; determining a target detection area based on at least the first predicted track, and determining a first target tracking vehicle based on detection of the target detection area; wherein, based on the first motion data, the low-speed calibration value and the high-speed calibration value, determining a first curvature of the own vehicle when running currently comprises one of the following conditions: in response to the running speed being less than or equal to the low-speed calibration value, acquiring a first yaw rate of the own vehicle, acquiring a first ratio of the first yaw rate to the running speed, and taking the first ratio as a first curvature of the own vehicle; in response to the running speed being greater than or equal to the high-speed calibration value, acquiring a second yaw rate of the own vehicle, and acquiring a second ratio of the second yaw rate to the running speed, wherein the second ratio is used as a first curvature of the own vehicle; and in response to the running speed being greater than the low-speed calibration value and less than the high-speed calibration value, determining a first weight of the first yaw rate affecting the first curvature and a second weight of the second yaw rate affecting the first curvature, weighting the first yaw rate and the second yaw rate by using the first weight and the second weight to obtain a weighted yaw rate, and obtaining a third ratio of the weighted yaw rate to the running speed as the first curvature of the own vehicle.

Wherein, before predicting the running track of the own vehicle in a preset time period in the future based on at least the first curvature to obtain a first predicted track, the method further comprises: determining a first curvature change rate when the own vehicle is currently running based on the first motion data, the low-speed calibration value and the high-speed calibration value; predicting a driving track of the own vehicle in a future preset time period based on at least the first curvature to obtain a first predicted track, wherein the method comprises the following steps: and predicting to obtain a first predicted track based on the first curvature and the first curvature change rate.

Wherein determining a first weight of the first yaw rate affecting the first curvature and a second weight of the second yaw rate affecting the first curvature comprises: acquiring a first difference value of the running speed and a low-speed calibration value and a second difference value of the high-speed calibration value and the low-speed calibration value; acquiring a fourth ratio of the first difference value and the second difference value, and taking the fourth ratio as a second weight; determining a first weight based on the second weight; wherein the first weight is inversely related to the second weight.

The first motion data comprise the running speed of the own vehicle at the current moment, vehicle parameters and the front wheel turning angle variation; determining a first curvature change rate when the own vehicle is currently running based on the first motion data, the low-speed calibration value and the high-speed calibration value, comprising: determining a yaw acceleration reference value of the own vehicle based on the vehicle parameter and the front wheel angle variation; determining a weight-related parameter of the yaw rate acceleration of the own vehicle at the current moment based on the running speed, the low-speed calibration value and the high-speed calibration value, wherein the yaw rate acceleration is inversely related to the weight-related parameter; determining the yaw acceleration of the own vehicle at the current moment based on the weight related parameters and the yaw acceleration reference value; and obtaining a fifth ratio of the yaw acceleration to the running speed, and taking the fifth ratio as the first curvature change rate.

The weight association parameter of the yaw acceleration of the own vehicle at the current moment is determined based on the relation between the running speed and the low-speed calibration value and the high-speed calibration value, and the weight association parameter comprises one of the following components: determining a weight-related parameter as a first constant in response to the travel speed being less than or equal to a low-speed calibration value; determining the weight-related parameter as a second constant in response to the travel speed being greater than or equal to the high-speed calibration value; in response to the running speed being greater than the low-speed calibration value and less than the high-speed calibration value, obtaining a first difference between the running speed and the low-speed calibration value and a second difference between the high-speed calibration value and the low-speed calibration value; and obtaining a fourth ratio of the first difference value and the second difference value, and taking the fourth ratio as a weight association parameter.

Wherein the future preset time period comprises a plurality of predicted time periods, each of which is composed of a plurality of future time points; based on the first curvature and the first curvature change rate, predicting to obtain a first predicted track includes: determining a second curvature of each future point in time based on the first curvature, the first curvature change rate, and preset influence parameters of the first curvature change rate at different points in time, wherein the different points in time comprise the current moment and each future point in time; based on the first curvature and each second curvature, determining coordinates of a plurality of control points corresponding to each prediction time period respectively; and determining a first predicted track by utilizing coordinates of a plurality of control points corresponding to each predicted time period.

Wherein determining the second curvature for each future point in time based on the first curvature, the first curvature rate of change, and the preset influencing parameters of the first curvature rate of change at different points in time, comprises: for each future time point, determining a third curvature of a previous time point of the future time point and preset influence parameters corresponding to different time points; if the previous time point is not the current time point, the second curvature corresponding to the previous time point is the third curvature; obtaining the product of the first curvature change rate and a corresponding preset influence parameter; and determining the addition result of the third curvature and the product, and taking the addition result as the second curvature of the future time point.

The first motion data comprise the running speed of the own vehicle at the current moment; based on the first curvature and each second curvature, determining coordinates of a plurality of control points corresponding to each predicted time period respectively, including: and determining coordinates of a plurality of control points corresponding to each prediction time period respectively based on the first curvature and each second curvature in response to the running speed being greater than or equal to a preset speed threshold.

The first motion data comprise the running speed of the own vehicle at the current moment; predicting a driving track of the own vehicle in a future preset time period based on at least the first curvature to obtain a first predicted track, wherein the method comprises the following steps: determining a course angle change amount of the own vehicle based on the shortest safety detection distance and the first curvature in response to the running speed being smaller than a preset speed threshold, wherein the course angle change amount is the course angle change amount of the current position and the end position when the own vehicle runs from the current position to the end position corresponding to the shortest safety detection distance; and determining the positions of a plurality of control points based on the course angle variation and the curvature radius corresponding to the first curvature.

Wherein before determining the target detection zone based at least on the first predicted trajectory, it comprises: responding to the current frame and the second target tracking vehicle existing in the previous history frame of the current frame, and acquiring second motion data of the second target tracking vehicle relative to the own vehicle at the current moment, wherein the second target tracking vehicle is the first target tracking vehicle in the previous history frame, and the second motion data comprises at least one of position data and an included angle; determining a second predicted track based on the second motion data and the first motion data, the second predicted track characterizing a predicted track of the host vehicle at which the host vehicle travels to the second target tracking vehicle according to the first motion data; determining an object detection region based at least on the first predicted trajectory, comprising: an object detection region is determined based on the first predicted trajectory and the second predicted trajectory.

Wherein the first predicted track comprises a plurality of track points; determining the target detection region based on the first predicted trajectory and the second predicted trajectory, comprising: taking at least part of track segments of the second predicted track as a first detection center line, and respectively determining a first detection boundary line on two sides of the first detection center line based on first preset detection data; determining the ratio of the number of first track points to the number of second track points, wherein the number of the first track points is the number of track points positioned between two first detection boundary lines in the first predicted track, and the number of the second track points is the total number of track points contained in the first predicted track; determining the first predicted track or the second predicted track as a second detection center line based on the ratio; and determining a target detection area based on the second detection center line, the driving situation of the own vehicle and second preset detection data corresponding to the driving situation of the own vehicle.

Wherein determining, based on the ratio, the first predicted trajectory or the second predicted trajectory as the second probe centerline comprises one of: determining the first predicted track as a second detection center line in response to the ratio being less than or equal to a preset threshold; and determining the second predicted track as a second detection center line in response to the ratio being greater than a preset threshold.

In order to solve the technical problems, the application adopts a further technical scheme that: there is provided an electronic device comprising a memory and a processor coupled to each other, the memory storing program instructions; the processor is configured to execute the program instructions stored in the memory to implement the above-described method.

In order to solve the technical problems, the application adopts another technical scheme that: there is provided a computer readable storage medium storing program instructions executable to implement the above method.

According to the scheme, the first curvature of the vehicle when the vehicle is currently running is determined according to the first motion data, the low-speed calibration value and the high-speed calibration value of the current moment of the vehicle, a first predicted track of a future preset time period of the vehicle is obtained at least based on the first curvature prediction, and after a target detection area is determined at least based on the first predicted track, target tracking vehicle selection is performed according to the determined target detection area. Compared with a mode of determining the first curvature by using the first motion data only, the first curvature determined according to the first motion data, the low-speed calibration value and the high-speed calibration value at the current moment of the vehicle is more accurate, and further after the target detection area is determined at least based on the first curvature, the first target tracking vehicle which is determined by detecting based on the target detection area is more accurate, and particularly in a lane-free scene, the target tracking vehicle can be accurately determined.

Drawings

FIG. 1 is a flow chart of an embodiment of a method for selecting a target tracking vehicle according to the present application;

FIG. 2 is a flow chart of an embodiment of predicting a first predicted trajectory based on a first curvature and a first curvature change rate provided by the present application;

FIG. 3 is a flowchart illustrating an embodiment of the step S14 shown in FIG. 1;

FIG. 4 is a schematic view of a first detected centerline and a first detected boundary line provided by the present application;

FIG. 5 is a schematic illustration of a target detection zone provided by the present application;

FIG. 6 is a flowchart illustrating an embodiment before step S13 shown in FIG. 1;

FIG. 7 is a schematic diagram of a frame of an embodiment of a target tracking vehicle selection device according to the present application;

FIG. 8 is a schematic diagram of a frame of an embodiment of an electronic device provided by the present application;

fig. 9 is a schematic diagram of a framework of a computer-readable storage medium provided by the present application.

Detailed Description

In order to make the objects, technical solutions and effects of the present application clearer and more specific, the present application will be described in further detail below with reference to the accompanying drawings and examples.

In addition, if there is a description of "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present application.

Referring to fig. 1, fig. 1 is a flowchart of an embodiment of a target tracking vehicle selecting method according to the present application. It should be noted that, if there are substantially the same results, the present embodiment is not limited to the flow sequence shown in fig. 1. As shown in fig. 1, the present embodiment includes:

s11: first motion data obtained from a current time of the vehicle.

The embodiment is used for determining a target detection area according to first motion data, a low-speed calibration value and a high-speed calibration value at the current moment of the vehicle, detecting the target detection area and determining a first target tracking vehicle.

The vehicle is a vehicle currently driven by using an automatic driving assistance system, the first motion data is parameter data when the vehicle is driven at the current moment, wherein the first motion data may, but is not limited to, include a driving speed when the vehicle is driven at the current moment, and may also include data such as a vehicle parameter (e.g. a vehicle mass, cornering stiffness of front and rear wheels, etc.), a front wheel corner or a front wheel corner variation amount of the vehicle at the current moment, where the first motion data may be obtained directly by each relevant sensor installed on the vehicle or obtained by relevant calculation, and specific data included in the first motion data and a corresponding obtaining mode need to be determined according to actual needs, and are not limited specifically herein.

In one embodiment, the first motion data and subsequent steps obtained from the current time of the vehicle are performed when it is detected that there is a blur, a lack of, a blockage or a break in the lane line of the current lane. Of course, in other embodiments, the first movement data obtained from the current time of the vehicle may be continuously executed regardless of the lane line.

S12: a first curvature of the host vehicle when currently traveling is determined based on the first motion data, the low-speed calibration value, and the high-speed calibration value.

The low speed calibration value is herein a reference value for determining whether the own vehicle is traveling at a low speed (at a lower speed), and the high speed calibration value is a reference value for determining whether the own vehicle is traveling at a high speed (at a higher speed). For example, if the low speed calibration value is 30km/h, the own vehicle can be considered to be traveling at a low speed when the traveling speed of the own vehicle is less than or equal to 30 km/h; for another example, if the high-speed calibration value is 100km/h, the own vehicle can be considered to be traveling at a high speed when the traveling speed of the own vehicle is greater than or equal to 100 km/h. It should be noted that the above-mentioned low-speed calibration value and high-speed calibration value are only used as examples, and the numerical values corresponding to the two calibration values can be determined according to actual situations, which are not limited specifically herein.

In this embodiment, the first motion data includes a travel speed at the time of the own vehicle traveling at the current time. The first curvature of the own vehicle when currently traveling may be obtained from the yaw rate of the own vehicle at the current time and the traveling speed of the own vehicle at the current time. The yaw rate of the own vehicle at the current time may be obtained by a corresponding sensor (for example, a yaw rate sensor), but due to reasons such as sensor detection sensitivity, the value directly obtained by the yaw rate sensor is more accurate at a higher running speed (the running speed is greater than or equal to the high-speed calibration value), but when the own vehicle runs at a non-higher speed (less than the high-speed calibration value), the result of the yaw rate directly obtained by the yaw rate sensor is not accurate enough, so that, in order to improve the accuracy of the yaw rate value at the current time, after the own vehicle is running at the current time, the yaw rate of the own vehicle at the current time may be determined according to the relationship between the running speed at the current time and the two calibration values (the low-speed calibration value and the high-speed calibration value), and further, the yaw rate of the own vehicle at the current time and the running speed at the current time are utilized to determine the first curvature at the current running time.

Optionally, step S12 determines, based on the first motion data, the low-speed calibration value and the high-speed calibration value, a first curvature when the own vehicle is currently running, including one of the following cases:

first, if the running speed of the own vehicle at the current moment is smaller than or equal to a low-speed calibration value, a first yaw rate of the own vehicle is obtained, then a first ratio of the first yaw rate to the running speed at the current moment is obtained, and the first ratio is used as a first curvature of the own vehicle when the own vehicle runs at the current moment.

In an embodiment, the first motion data further includes a vehicle parameter and a front wheel rotation angle when the vehicle is running at the current moment, and when the running speed of the vehicle is less than or equal to the low-speed calibration value, the calculation of the yaw rate can be performed by means of a two-degree-of-freedom model of the vehicle, so as to improve the accuracy of the yaw rate determined under the condition of the running speed. Specifically, a first yaw rate of the own vehicle is determined according to a vehicle parameter and a front wheel rotation angle when the own vehicle runs at the current moment, and the first yaw rate is used as the yaw rate of the own vehicle at the current moment, so that the accuracy of a first curvature when the own vehicle runs at the current moment is determined by using a first ratio of the first yaw rate to the running speed at the current moment.

For example, in the case where the running speed is less than or equal to the low-speed calibration value, the yaw rate of the own vehicle at the present time (first yaw rate) may be determined using the vehicle parameters and the front wheel rotation angle in the following formulas:

wherein ω is a first yaw rate, v_host is a current traveling speed of the host vehicle, a and b are lengths of front and rear axes of the vehicle, respectively, C _f ,C _r Respectively the cornering stiffness of front and rear wheels of the vehicle, m is the mass of the whole vehicle, delta _f Is the front wheel corner, wherein a, b and C _f And C _r And m are vehicle parameters when the vehicle runs at the current moment.

And if the running speed of the own vehicle at the current moment is greater than or equal to the high-speed calibration value, acquiring a second yaw rate of the own vehicle, acquiring a second ratio of the second yaw rate to the running speed, and taking the second ratio as the first curvature of the own vehicle.

Since the running speed of the own vehicle is at a higher running speed (the running speed is greater than or equal to the high-speed calibration value), the value directly obtained by the yaw rate sensor is more accurate, and therefore, if the running speed of the own vehicle at the current time is greater than or equal to the high-speed calibration value, the second yaw rate output by the yaw rate sensor can be directly used as the yaw rate of the own vehicle at the current time, and the first curvature when the own vehicle is currently running can be determined by using the second yaw rate.

Thirdly, if the running speed of the vehicle at the current moment is greater than the low-speed calibration value and less than the high-speed calibration value, determining a first weight of the first yaw rate influencing the first curvature and a second weight of the second yaw rate influencing the first curvature, weighting the first yaw rate and the second yaw rate by using the first weight and the second weight to obtain a weighted yaw rate, and obtaining a third ratio of the weighted yaw rate to the running speed as the first curvature of the vehicle.

It should be noted that, as is clear from the above description, the yaw rate at the current running speed can be accurately determined in the following two cases. The first case is: under the condition that the speed is smaller than or equal to the low-speed calibration value, the calculated yaw rate value is more accurate by means of a two-degree-of-freedom model of the vehicle; the second case is: at higher running speeds (running speeds greater than or equal to the high-speed calibration value), the yaw rate value obtained by the yaw rate sensor is relatively accurate; therefore, in order to improve the accuracy of the yaw rate obtained by the running speed in the case other than the above two cases, the first weight of the first curvature influence of the first yaw rate determined according to the first case and the second weight of the first curvature influence of the second yaw rate determined according to the second case may be determined first, then the first yaw rate and the second yaw rate are weighted by the first weight and the second weight to obtain the weighted yaw rate, and the third ratio of the weighted yaw rate to the running speed is determined as the first curvature of the own vehicle.

The process of determining the first weight of the first yaw rate affecting the first curvature and the second weight of the second yaw rate affecting the first curvature will be described below in conjunction with the following second weight formula:

where weight represents the second weight, v_host represents the current running speed of the own vehicle, v_min represents the low-speed calibration value, and v_max represents the high-speed calibration value.

Firstly, acquiring a first difference value of the current running speed and a low-speed calibration value of a self-vehicle and a second difference value of a high-speed calibration value and a low-speed calibration value; and then obtaining a fourth ratio of the first difference value and the second difference value, wherein the fourth ratio is the second weight, and then determining the first weight based on the second weight. Wherein the first weight is inversely related to the second weight, and the sum of the first weight and the second weight is a constant (e.g., 1).

S13: and predicting the running track of the own vehicle in a future preset time period based on at least the first curvature to obtain a first predicted track.

The future preset time period herein indicates a future period of time corresponding to the predicted first predicted track, and the time range indicated by the specific future preset time period may be set according to the actual situation, for example, if the track corresponding to the driving 5s of the vehicle is to be predicted, the future preset time period may be the future 5s, if the distance of the predicted track in a shorter time period is considered to be shorter in consideration of the low-speed driving of the vehicle, so that the detection range is closer (smaller), the prediction time may be appropriately lengthened according to the actual situation, that is, the future preset time period may be set to be a longer time period so as to increase the detection range.

In an embodiment, in a scenario where the setting of the time range of the future preset time does not consider the running speed of the own vehicle, if the current running speed of the own vehicle is smaller than the preset speed threshold, the running track of the own vehicle in the future preset time period may be predicted based on the first curvature, so as to obtain the first predicted track.

If the current running speed of the own vehicle is smaller than the preset speed threshold, when track prediction is performed according to the first curvature of the current running speed and a preset time period in the future, the track length of the predicted first predicted track is not smaller than the shortest safety detection distance. The shortest safety detection distance is the shortest distance that can perform safety detection, and if the track length of the first predicted track is shorter than the shortest safety detection distance, a detection range determined by the current shorter predicted track length is smaller, it is easy to cause a vehicle that is closer to the own vehicle to be out of the detection range, so that the own vehicle considers that there is no target tracking vehicle ahead, and in this case, if the own vehicle accelerates, it is easy to cause a hazard. For example, if the actual distance from the preceding vehicle to the own vehicle is 10 meters, and the current traveling speed of the own vehicle is too small, and the distance traveled by the own vehicle at the current speed (the length of the corresponding predicted trajectory) for the future preset time is 5 meters, the own vehicle will generate a target detection area within a range of 5 meters from the own vehicle, vehicles beyond 5 meters will not be selected as target tracking vehicles, and if the own vehicle travels at the original traveling speed or accelerates, the own vehicle will find that the target tracking vehicle is decelerating only when the own vehicle is 5 meters from the preceding vehicle, but will collide with the target tracking vehicle easily at this time.

Therefore, in this embodiment, in order to improve the safety of the vehicle running, when the current running speed of the vehicle is less than the preset speed threshold, the heading angle change amounts of the start point and the end point are predicted first when the vehicle runs from the current time position (start point) to the end point position corresponding to the shortest safety detection distance under the current first curvature, then the coordinates of a plurality of control points are determined according to the heading angle change amounts and the curvature radius corresponding to the first curvature (generally, a section of predicted track needs to be determined by the coordinates of 4 control points), and then the first predicted track is determined by a third-order bezier curve formula.

After the course angle change amount is determined, the coordinates of each control point can be determined according to the following formula according to the course angle change amount and the curvature radius corresponding to the first curvature:

(p_x0_ego，p_y0_ego)＝(0，0)

(p_x1_ego，p_y1_ego)＝(0.4p_x3_ego，0)

(p_x3_ego，p_y3_ego)＝(R*sin(θ _ego )，R*(1-cos(θ _ego )))

wherein (p_x0_ ego, p_y0_ ego) represents the coordinates of the first control point, the coordinates of the current position of the vehicle, (p_x1_ ego, p_y1_ ego) represents the coordinates of the second control point, (p_x2_ ego, p_y2_ ego) represents the coordinates of the third control point, and (p_x3_ ego, p_y3_ ego) represents the coordinates of the fourth control point, the coordinates of the vehicle at the current first curvature, the coordinates of the vehicle at the time of traveling from the current position to the end position corresponding to the shortest safety detection distance, R represents the radius of curvature corresponding to the first curvature, θ _ego Indicating the amount of change in heading angle.

It should be noted that, each coordinate herein is based on a coordinate in the vehicle coordinate system, and the vehicle coordinate system may be established by taking the center of the front axle of the vehicle as the origin of coordinates, taking the forward direction as the positive direction of the X-axis, and taking the left direction as the positive direction of the y-axis, or, of course, taking other positions of the vehicle as the origin of coordinates.

The first predicted track is determined by a third-order Bezier curve formula, as follows:

x_ego＝p _{0x_t} (1-τ) ³ +3p _{1x_t} (1-τ) ² τ+3p _{2x_t} (1-τ)τ ² +3p _{3x_t} τ ³

y_ego＝p _{0y_t} (1-τ) ³ +3p _{1y_t} (1-τ) ² τ+3p _{2y_t} (1-τ)τ ² +3p _{3y_t} τ ³

where (x_ ego, y_ ego) denotes the coordinates of the first predicted track, (p) _{0x_t} ，p _{0y_t} ) Representing the coordinates of the first control point within a preset future time t, similarly, (p _{1x_t} ，p _{1y_t} ) Representing the coordinates of the second control point, (p) _{2x_t} ，p _{2y_t} ) Representing the coordinates of the third control point, (p) _{3x_t} ，p _{3y_t} ) Representing the coordinates of the fourth control point.

In another embodiment, before step S13, a first curvature change rate when the own vehicle is currently running may be determined based on the first motion data, the low-speed calibration value, and the high-speed calibration value, and then, a first predicted trajectory is predicted based on the first curvature and the first curvature change rate.

Referring to fig. 2, fig. 2 is a flowchart illustrating an embodiment of predicting a first predicted trajectory based on a first curvature and a first curvature change rate according to the present application. It should be noted that, if there are substantially the same results, the embodiment is not limited to the flow sequence shown in fig. 2. As shown in fig. 2, the present embodiment includes:

S21: the second curvature for each future point in time is determined based on the first curvature, the first curvature rate of change, and preset influencing parameters of the first curvature rate of change at different points in time. The different points in time include a current time and future points in time.

The embodiment is used for determining coordinates of a plurality of control points corresponding to each prediction time period respectively based on the first curvature, the first curvature change rate and preset influence parameters of the first curvature change rate at different time points, and further predicting to obtain a first prediction track according to each control point.

In this embodiment, the future preset time period may be divided into a plurality of predicted time periods, each of which is composed of a plurality of future time points. For example, to predict the trajectory corresponding to the traveling 5s of the own vehicle, the future preset time period is 0-5s, and the 0-5s may be divided into 5 prediction time periods, which are respectively 0-1s, 1-2s, 2-3s, 3-4s, and 4-5s, and each time period is composed of at least one future time point.

It should be noted that, the present embodiment is applicable to a scenario in which the running speed of the own vehicle is greater than a preset speed threshold, where in the scenario, the distance of the first preset track predicted based on the first curvature and the first curvature change rate at the current running speed is greater than the shortest safety detection distance, and in the case where the distance of the first preset track is greater than the shortest safety detection distance, the safety of the running of the own vehicle can be ensured based on the detection distance.

Meanwhile, it should be noted that the curvature change rate corresponds to the movement trend of the vehicle tire, that is, is associated with the movement trend of the vehicle steering wheel, for example, the steering wheel is likely to be rotated in a short time (for example, within 1s or 2 s), but then the steering wheel is not rotated with the trend any more, so that considering the rotation situation of the vehicle steering wheel in an actual driving scene, in this embodiment, the curvature change rate at different time points is determined by the preset influence parameters of the first curvature change rate at different time points from the current time point, and further, the second curvature at each future time point is determined by the first curvature, the first curvature change rate, and the preset influence parameters of the first curvature change rate at different time points. Wherein the different time points comprise a current time point and each future time point, and the curvature of the current time point is known as a first curvature change rate.

In one embodiment, the process of determining the second curvature for each future point in time includes the steps of:

to facilitate an understanding of the process of determining the second curvature for each future point in time, the following equations will now be described:

Where t represents different points in time, t=0 represents the current point in time, kappa represents the first curvature,t.noteq.0 represents the non-current time point, kappa _t Representing a second curvature, kappa, of each future point in time _t-1 A third curvature at a previous time point, and (k) represents a first curvature change rate _t A preset influencing parameter representing a first rate of change of curvature at different points in time. Wherein when t=0, the preset influence parameter of the first curvature change rate at the corresponding time point is 1, when t=1, the preset influence parameter of the first curvature change rate at the corresponding time point is-1, when t>1, the preset influence parameter of the first curvature change rate at the corresponding time point is 0, which indicates that when t>1, the curvature change rate is not changed from the previous time point.

Wherein determining the second curvature for each future point in time comprises the steps of:

first, for each future point in time, determining a third curvature kappa at a point in time prior to the future point in time _t-1 Preset influencing parameter k corresponding to future time point _t The method comprises the steps of carrying out a first treatment on the surface of the And if the previous time point is not the current time point, the second curvature corresponding to the previous time point is the third curvature.

Second, obtaining the product k of the first curvature change rate and the corresponding preset influence parameter _t kappa_rate。

Third, determine the sum of the third curvature and the product kappa _t-1 +k _t kappa_rate, and taking the addition result as a second curvature kappa at a future point in time _t 。

It can be understood that the second curvature of each future time point is determined according to the third curvature of the previous time point and the preset influence parameters corresponding to different time points, wherein if the previous time point of the future time point is the current time point, the third curvature of the previous time point is the first curvature of the current time point, and if the previous time point is not the current time point, the second curvature of the previous time point is the third curvature of the previous time point.

S22: and determining coordinates of a plurality of control points corresponding to each prediction time period respectively based on the first curvature and each second curvature.

In this embodiment, when the current running speed of the own vehicle is greater than or equal to the preset speed threshold (at this time, the distance of the predicted first preset track is greater than the shortest safety detection distance), the coordinates of a plurality of control points corresponding to each predicted time period may be determined based on the first curvature and each second curvature.

For convenience of explanation, a process of determining coordinates of a plurality of control points corresponding to each prediction period will be described by taking a future preset time of 2s as an example.

Taking the current time to the future time point 1s as a first prediction time period, for the first prediction time period, under the condition that the first curvature of the current time and the second curvature of the future time point 1s are determined, determining the running condition (straight running or curve running) of the vehicle according to the relation between the first curvature and the second curvature and a preset curvature threshold value respectively, and then predicting the position (coordinate) of the vehicle running to the future time point 1s by combining the running condition and the related kinematics principle, wherein the position of the current time is the position of the first control point of the first prediction time period, the position of the vehicle at the future time point 1s is the position of the fourth control point, and then determining the coordinates of the second control point and the coordinates of the third control point by using the coordinates of the first control point and the fourth control point. Similarly, the coordinates of a plurality of control points corresponding to the second predicted period are determined based on the same prediction principle as the first predicted period, with the future time point 1s to the future time point 2s as the second predicted period, and the coordinates of the fourth control point of the first predicted period as the coordinates of the first control point of the second predicted period.

Wherein for the first predicted time period, determining the driving condition (whether straight driving or curved driving) of the own vehicle according to the relation between the first curvature and the second curvature and the preset curvature threshold value respectively includes: if the first curvature and the second curvature are smaller than the preset curvature threshold value, the self-vehicle is considered to be in straight line driving in the prediction time period; if one of the first curvature and the second curvature is greater than or equal to the preset curvature threshold, the predicted time period is considered to be a curve running, and the specific threshold of the preset curvature threshold can be determined according to the accuracy of the judgment result, which is not particularly limited herein.

Preferably, in one embodiment, to ensure the smoothness (continuity of track derivative and curvature) of the predicted track splice point for each time period, the second and third control point coordinates may be confirmed by taking the first and second order partial derivatives for the curve coefficient port of the third order bezier curve. Wherein, the third-order Bezier curve is expressed as follows:

wherein (x_ ego, y_ ego) represents the coordinates of each trace point on the Bezier curve, (p) _{0x_t} ，p _{0y t} ) Representing the coordinates of the first control point, (p) _{1x t} ，p _{1y t} ) Representing the coordinates of the second control point, (p) _{2x_t} ，p _{2y_t} ) Representing the coordinates of the third control point, (p) _{3x_t} ，p _{3y_t} ) Representing the coordinates of the fourth control point. After the first-order bias and the second-order bias are obtained for the curve coefficient port of the third-order bezier curve, ∈0 may be taken to confirm the coordinates of the second control point and the third control point.

S23: and determining a first predicted track by utilizing coordinates of a plurality of control points corresponding to each predicted time period.

In this embodiment, after determining coordinates of a plurality of control points corresponding to each of the predicted time periods, a motion track of the vehicle in each of the predicted time periods is determined by using a third-order bezier curve, and then the motion tracks in each of the predicted time periods are combined according to a time sequence to determine a first predicted track.

Wherein, the motion trail of the vehicle in each prediction time period is determined as follows:

wherein (x_ ego, y_ ego) represents the coordinates of the motion trail of each predicted period, (p) _{0x_t} ，p _{0y_t} ) Representing the coordinates of the first control point of each predicted time period, and is similar, (p _{1x_t} ，p _{1y_t} ) Representing the coordinates of the second control point, (p) _{2x_t} ，p _{2y_t} ) Representing the coordinates of the third control point, (p) _{3x_t} ，p _{3y_t} ) Representing the coordinates of the fourth control point.

S14: the target detection area is determined based at least on the first predicted trajectory, and the first target tracking vehicle is determined based on the detection of the target detection area.

In an embodiment, before step S14, if there is a second target tracking vehicle in the current frame acquired at the current time and in a previous history frame of the current frame, second motion data of the second target tracking vehicle relative to the own vehicle at the current time may be acquired, and then, based on the second motion data and the first motion data, a second predicted track of the own vehicle from traveling to the second target tracking vehicle according to the first motion data is determined. The second target tracking vehicle is a first target tracking vehicle in a previous history frame, and the second motion data includes at least one of position data and an included angle, that is, if the second target tracking vehicle exists in the current frame and the previous history frame of the current frame, at least one of a position and an included angle of the second target tracking vehicle relative to the own vehicle at the current moment needs to be obtained.

In one embodiment, the second motion data includes a position (coordinate) of the second target tracking vehicle and an angle between the second target tracking vehicle and the own vehicle, and determining, based on the second motion data and the first motion data, a second predicted trajectory of the own vehicle traveling to the second target tracking vehicle according to the first motion data includes: firstly, a plurality of control points related to a second predicted track are determined according to the coordinates of a second target tracking vehicle, the included angle between the second target tracking vehicle and a vehicle and related limiting data, and then the second predicted track is determined through a third-order Bezier curve.

The following describes determining a number of control points about the second predicted trajectory based on the coordinates of the second target tracked vehicle, the angle between the second target tracked vehicle and the host vehicle, and the associated limiting data, in conjunction with the following equations:

(p_x0，p_y0)＝(0，0)

(p_x1，p_y1)＝(pos_x_lead/2，0)

(p_x3，p_y3)＝(pos_x_lead，y_lead)

wherein (p_xi, p_yi) is the coordinates of each control point, (pos_x_lead, pos_y_lead) is the coordinates of the second target tracking vehicle, θ _lead Representing the predicted included angle between the second target track and the own vehicle (used for fitting the second predicted track) when the second predicted track is fitted, theta _{lead_to_ego} And (3) for tracking the included angle between the vehicle and the own vehicle for the second target, wherein PI is the circumference rate, and y_bound is the preset calibration distance.

Wherein, θ _lead The function of the predicted included angle is to limit the predicted included angle between the two target tracking vehicles and the own vehicle, and the generated track is more reasonable by limiting the included angle between the second target tracking vehicle and the own vehicle.

In an embodiment, after determining that the host vehicle is traveling to a second predicted trajectory at the second target tracking vehicle according to the first motion data, the target detection area may be determined based on the first predicted trajectory and the second predicted trajectory. And after the target detection area is determined, detecting based on the target detection area, and determining the first target tracking vehicle. The first target tracking vehicle is a vehicle which is selected to run in a preset time period in the future and is to be tracked.

According to the scheme, the first curvature of the vehicle when the vehicle is currently running is determined according to the first motion data, the low-speed calibration value and the high-speed calibration value of the current moment of the vehicle, a first predicted track of a future preset time period of the vehicle is obtained at least based on the first curvature prediction, and after a target detection area is determined at least based on the first predicted track, target tracking vehicle selection is performed according to the determined target detection area. Compared with the mode of determining the first curvature by using the first motion data only, the first curvature determined according to the first motion data, the low-speed calibration value and the high-speed calibration value at the current moment of the vehicle is more accurate, and further after the target detection area is determined at least based on the first curvature, the first target tracking vehicle which is determined by detecting based on the target detection area is more accurate, and particularly in a lane-free scene, the target tracking vehicle can be accurately determined.

Referring to fig. 3, fig. 3 is a flowchart illustrating an embodiment of step S14 shown in fig. 1. It should be noted that, if there are substantially the same results, the embodiment is not limited to the flow sequence shown in fig. 3. As shown in fig. 3, in the present embodiment, determining the target detection area based on the first predicted trajectory and the second predicted trajectory includes:

S31: and taking at least part of track sections of the second predicted track as a first detection center line, and respectively determining a first detection boundary line on two sides of the first detection center line based on first preset detection data.

In an embodiment, please refer to fig. 4 in combination, fig. 4 is a schematic diagram of a first detection center line and a first detection boundary line provided by the present application. After determining that the own vehicle runs to a second predicted track at the second target tracking vehicle according to the first motion data, taking at least part of track segments of the second predicted track as a first detection center line, and determining a first detection boundary line on two sides of the first detection center line according to first preset detection data. The first preset detection data is used for limiting detection boundaries at two sides, can be determined according to the accuracy of selection of a subsequent detection center line, and is not particularly limited.

In another embodiment, after determining the second predicted track and the first predicted track, track segments with the same distance length in the two predicted tracks may be selected as the first detection center line, and then, based on the first preset detection data, one first detection boundary line is determined on each side of the first detection center line.

S32: and determining the ratio of the number of the first track points to the number of the second track points, wherein the number of the first track points is the number of track points positioned between the two first detection boundary lines in the first predicted track, and the number of the second track points is the total number of track points contained in the first predicted track.

In this embodiment, the number of first track points between the two first detection boundary lines and the number of second track points (total number of track points) included in the first predicted track are determined first, and then the ratio of the number of first track points to the number of second track points is determined based on the number of first track points and the number of second track points.

S33: based on the ratio, the first predicted trajectory or the second predicted trajectory is determined to be the second probe centerline.

If the ratio of the number of the first track points to the number of the second track points is larger than a preset threshold value, the driving intention of the future preset time period of the vehicle is consistent with the driving intention corresponding to the second predicted track, and in this case, the second predicted track is taken as a second detection center line; otherwise, if the ratio of the number of the first track points to the number of the second track points is smaller than or equal to the preset threshold, the driving intention of the future period of the vehicle and the driving intention corresponding to the second predicted track are indicated to have a low degree of coincidence, and in this case, the first predicted track corresponding to the first curvature, which is at least based on the current time, is directly used as the second detection center line.

S34: and determining a target detection area based on the second detection center line, the running condition of the own vehicle and corresponding second preset detection data.

The second preset detection data comprises different calibration offset distance sets at two sides of the second detection center line, so that 4 second detection boundary lines are determined through the different calibration offset distance sets. Referring to fig. 5, fig. 5 is a schematic diagram of a target detection area provided by the present application. The object detection area comprises an inner detection area and an outer detection area which are formed by different second detection boundary lines, the area formed by two second detection boundary lines which are closer to the second detection center line is an inner detection area, and the area formed by two second detection boundary lines which are farther from the second detection center line is an outer detection area.

The driving situation of the vehicle is, for example, turning (left turning, right turning), straight running, or head drop. Under different driving conditions, the corresponding calibration offset distance sets at two sides of the second detection center line are different, for example, under the condition that the vehicle is running straight, the calibration offset distance sets at two sides of the second detection center line are data symmetrical to the second detection center line as a whole, and under the condition that the vehicle is turning left, compared with the condition that the vehicle is turning left, each calibration offset distance in the calibration offset distance set at the left side of the second detection center line is slightly larger than the calibration offset distance set at the right side of the second detection center line, and specific second preset detection data can be determined according to actual conditions, so that specific limitation is not made herein.

In the case where the distance between the second target vehicle and the host vehicle is short, the present embodiment can improve the accuracy of the first target tracking vehicle selection and the safety, compared to the case where the first target tracking vehicle is based on the first predicted trajectory alone. For example, when the second target vehicle is ahead and is closer to the own vehicle, and the second target vehicle is turning with the intention of turning, the steering wheel of the second target vehicle will generally operate earlier, and at this time, the second target vehicle may still be in a straight-ahead state when turning, and if the target detection area is determined by using only the first predicted track as the detection center line, the second target vehicle may not be in the target detection area, and if the second target vehicle is turning at the current speed, the second target vehicle may collide with the ahead second target vehicle. In the same scenario, if the second predicted track is considered in the process of determining the target detection area, since the second predicted track is predicted according to the current first motion data of the own vehicle and the current second motion data of the second target vehicle, the second target vehicle can be determined to be in-curve through the second predicted track, and the second target vehicle is in the target detection area determined by the second predicted track under the condition that the own vehicle has the same turning intention, and the second target vehicle can still be selected as the first target vehicle, so that the accuracy of selecting the first target tracking vehicle can be improved, and meanwhile, the danger of turning at the current speed of the own vehicle and colliding with the second target vehicle can be avoided.

In some embodiments, after determining the target detection zone, detecting based on the target detection zone, determining the first target tracking vehicle includes:

first, a candidate vehicle is determined. The detection may be performed using a detection device on the host vehicle to determine that a vehicle within a predetermined distance range (e.g., a predetermined distance from the host vehicle in front of and/or to the left and right of the host vehicle) is a candidate vehicle.

Second, a first target tracked vehicle is determined based on third motion data for each candidate vehicle. Wherein the third motion data includes a position of at least a portion of the candidate vehicle and a traveling direction, in the present embodiment, the candidate vehicle whose center position is located within the inner detection area or whose partial position is within the inner detection area and has a tendency to travel into the inner detection area is determined as the target vehicle; and under the condition that the candidate vehicle is positioned between the inner detection area and the outer detection area, if the candidate vehicle is the first target tracking vehicle in the previous or the previous preset number of historical frames of the current frame, selecting the candidate vehicle as the target vehicle, otherwise, not selecting the candidate vehicle as the target vehicle.

Of course, if the center position of the candidate vehicle is located outside the outer detection area or if the partial position of the candidate vehicle is located outside the outer detection area and tends to exit the outer detection area, the candidate vehicle is not selected as the target vehicle.

If a large number of target vehicles are determined through the above steps, the target vehicles are ranked according to the distance between each target vehicle and the own vehicle, and the target vehicle closest to the own vehicle is determined as the first target tracking vehicle for tracking.

Referring to fig. 6, fig. 6 is a flowchart illustrating an embodiment before step S13 shown in fig. 1. It should be noted that, if there are substantially the same results, the present embodiment is not limited to the flow sequence shown in fig. 6. As shown in fig. 6, the present embodiment includes:

s61: a yaw acceleration reference value of the own vehicle is determined based on the vehicle parameter and the front-wheel-rotation-angle variation amount.

The embodiment is used for determining a first curvature change rate when the vehicle is currently running based on the first motion data, the low-speed calibration value and the high-speed calibration value.

In this embodiment, the first motion data includes a running speed of the own vehicle, a vehicle parameter, and a front wheel angle change amount at the current time. The yaw rate value obtained by the yaw rate sensor is accurate under the condition that the differentiator is not designed, but the distance of the track to be predicted is far due to the fact that the speed is high, the track jitter of the far end is frequent, and the selection of a follow-up target tracking vehicle is not facilitated. Therefore, in this embodiment, the yaw rate reference value is obtained by using the more accurate calculation method (refer to the following formula in step S21) of the yaw rate under the assumption that the current running speed (assumed speed) is less than or equal to the low-speed calibration value, and then the weight-related parameter affecting the yaw rate is determined by combining the relationship between the current running speed (current actual running speed) and the two speed calibration values (low-speed calibration value and high-speed calibration value), and then the yaw rate (estimated value) under the current running speed is determined by using the weight-related parameter and the yaw rate reference value obtained under the assumption of the running speed.

Wherein, under the condition that the assumed running speed (assumed speed) is smaller than or equal to the low-speed calibration value, the current running speed of the own vehicle, the vehicle parameters and the front wheel angle change quantity are utilized to determine the yaw angle acceleration reference value of the own vehicle at the current moment as follows:

in the method, in the process of the invention,a and b are the front-rear axle length of the vehicle, C _f ，C _r Respectively the cornering stiffness of front and rear wheels of the vehicle, m is the mass of the whole vehicle, v_host is the current running speed of the own vehicle, and +.>Is the front wheel steering angle variation, wherein a, b and C _f And C _r And m are vehicle parameters when the vehicle runs at the current moment.

S62: and determining a weight-related parameter of the yaw acceleration of the vehicle at the current moment based on the running speed, the low-speed calibration value and the high-speed calibration value, wherein the yaw acceleration is inversely related to the weight-related parameter.

Note that, the yaw acceleration herein indicates an estimated yaw acceleration value of the own vehicle at the present time without any particular description.

Since the yaw-rate acceleration reference value determined in step S21 is an obtained yaw-rate acceleration reference value assuming that the current running speed (assumed speed) is less than or equal to the low-speed calibration value, after the yaw-rate acceleration reference value is obtained, a weight-related parameter affecting the yaw-rate acceleration is determined by combining the relationship between the actual running speed of the current vehicle and the two speed calibration values (low-speed calibration value and high-speed calibration value), wherein the yaw-rate acceleration is inversely related to the weight-related parameter, and the yaw-rate acceleration at the current running speed is determined by using the weight-related parameter and the obtained yaw-rate acceleration reference value.

Wherein, according to the relation between the current actual running speed of the self-vehicle and two speed calibration values (a low speed calibration value and a high speed calibration value), the weight association parameter affecting the yaw angle acceleration value is determined, and the following can be referred to:

where weight represents a weight-related parameter affecting yaw acceleration, v_min represents a low-speed calibration, v_max represents a high-speed calibration, and v_ost represents a current (actual) running speed.

When the running speed of the self-vehicle is smaller than or equal to the low-speed calibration value, determining the weight association parameter as a first constant; when the running speed is greater than or equal to the high-speed calibration value, determining the weight association parameter as a second constant; when the running speed is greater than the low-speed calibration value and less than the high-speed calibration value, a first difference value between the running speed and the low-speed calibration value and a second difference value between the high-speed calibration value and the low-speed calibration value are obtained, a fourth ratio of the first difference value to the second difference value is obtained, and the fourth ratio is used as the weight association parameter. The first constant and the second constant are parameters that indicate the importance degree of the yaw acceleration, the first constant may be, but not limited to, 0, the second constant may be, but not limited to, 1, and the second constant may be specifically adjusted according to the actual situation, and is not specifically limited herein.

S63: and determining the yaw acceleration of the own vehicle at the current moment based on the weight-related parameter and the yaw acceleration reference value.

In this embodiment, a process of determining the yaw acceleration, and determining the first curvature change rate when the own vehicle is currently running, based on the weight-related parameter, the yaw acceleration reference value, will be described in step S64 in conjunction with steps S23 and S24.

S64: and obtaining a fifth ratio of the yaw acceleration to the running speed, and taking the fifth ratio as the first curvature change rate.

The procedure of steps S23 and S24 can refer to the following formula:

where kappa_rate represents a first curvature change rate when the own vehicle is currently running, weight represents a weight-related parameter,the yaw acceleration reference value is represented, and v_host represents the current (actual) running speed. Wherein, the liquid crystal display device comprises a liquid crystal display device,the result of (2) indicates the yaw acceleration of the own vehicle at the current time.

Referring to fig. 7, fig. 7 is a schematic diagram of a frame of an embodiment of a target tracking vehicle selecting device according to the present application. In the present embodiment, the target tracked vehicle selection device 70 includes an acquisition module 71, a first determination module 72, a second determination module 73, and a third determination module 74. The acquisition module 71 is configured to acquire first motion data of a current moment of the own vehicle; the first determining module 72 is configured to determine a first curvature of the own vehicle when the own vehicle is currently running, based on the first motion data, the low-speed calibration value, and the high-speed calibration value; the second determining module 73 is configured to predict a driving track of the own vehicle in a future preset time period based at least on the first curvature, so as to obtain a first predicted track; the third determination module 74 is configured to determine an object detection zone based at least on the first predicted trajectory and determine a first object tracking vehicle based on the detection of the object detection zone.

In the above-mentioned scheme, the target tracking vehicle selecting device 70 may implement the steps in the above-mentioned target tracking vehicle selecting method embodiment, where the host vehicle may determine a target detection area according to the first motion data, the low-speed calibration value and the high-speed calibration value at the current time, and since the first curvature is determined according to the first motion data, the low-speed calibration value and the high-speed calibration value at the current time of the host vehicle, compared with a manner of determining the first curvature by using only the first motion data, the first curvature determined according to the first motion data, the low-speed calibration value and the high-speed calibration value at the current time of the host vehicle is more accurate, and further after determining the target detection area based on at least the first curvature, the first target tracking vehicle determined based on the target detection area is also more accurate, especially in a lane-free scenario, and the target tracking vehicle may be accurately determined.

In some embodiments, the second determining module 73 includes a determining submodule and a predicting submodule, where the determining submodule is configured to determine, before the second determining module 73 obtains the first predicted trajectory, a first curvature change rate when the vehicle is currently running based on the first motion data, the low-speed calibration value, and the high-speed calibration value; the prediction submodule is used for predicting and obtaining a first prediction track based on the first curvature and the first curvature change rate.

In some embodiments, the first motion data acquired by the acquisition module 71 includes at least a running speed of the own vehicle at the current time; the first determination module 72 determines a first curvature of the host vehicle when the host vehicle is currently traveling based on the first motion data, the low-speed calibration value, and the high-speed calibration value, including one of: in response to the running speed being less than or equal to the low-speed calibration value, acquiring a first yaw rate of the own vehicle, acquiring a first ratio of the first yaw rate to the running speed, and taking the first ratio as a first curvature of the own vehicle; in response to the running speed being greater than or equal to the high-speed calibration value, acquiring a second yaw rate of the own vehicle, and acquiring a second ratio of the second yaw rate to the running speed, wherein the second ratio is the first curvature of the own vehicle; and in response to the running speed being greater than the low-speed calibration value and less than the high-speed calibration value, determining a first weight of the first yaw rate affecting the first curvature and a second weight of the second yaw rate affecting the first curvature, weighting the first yaw rate and the second yaw rate by using the first weight and the second weight to obtain a weighted yaw rate, and obtaining a third ratio of the weighted yaw rate to the running speed as the first curvature of the own vehicle.

In some embodiments, the first determination module 72 determines a first weight of the first yaw rate that affects the first curvature and a second weight of the second yaw rate that affects the first curvature, comprising: acquiring a first difference value of the running speed and a low-speed calibration value and a second difference value of the high-speed calibration value and the low-speed calibration value; acquiring a fourth ratio of the first difference value and the second difference value, and taking the fourth ratio as a second weight; determining a first weight based on the second weight; wherein the first weight is inversely related to the second weight.

In some embodiments, the first motion data acquired by the acquisition module 71 includes a running speed of the own vehicle at the current time, a vehicle parameter, and a front wheel angle change amount; the first determining module 72 includes a first determining sub-module for determining a yaw acceleration reference value of the own vehicle based on the vehicle parameter and the front wheel angle variation, a second determining sub-module, a third determining sub-module, and an acquiring sub-module; the second determining submodule is used for determining weight-related parameters of the yaw acceleration of the own vehicle at the current moment based on the running speed, the low-speed calibration value and the high-speed calibration value, wherein the yaw acceleration is inversely related to the weight-related parameters; the third determining submodule is used for determining the yaw acceleration of the own vehicle at the current moment based on the weight-related parameter and the yaw acceleration reference value; the acquisition sub-module is used for acquiring a fifth ratio of yaw acceleration to running speed, and the fifth ratio is used as the first curvature change rate.

In some embodiments, the second determination submodule determines the weight-related parameter of the yaw acceleration based on the relationship of the travel speed to the low-speed calibration and the high-speed calibration, including one of: determining a weight-related parameter as a first constant in response to the travel speed being less than or equal to a low-speed calibration value; determining the weight-related parameter as a second constant in response to the travel speed being greater than or equal to the high-speed calibration value; in response to the running speed being greater than the low-speed calibration value and less than the high-speed calibration value, obtaining a first difference between the running speed and the low-speed calibration value and a second difference between the high-speed calibration value and the low-speed calibration value; and obtaining a fourth ratio of the first difference value and the second difference value, and taking the fourth ratio as a weight association parameter.

In some embodiments, the future preset time period comprises a plurality of predicted time periods, each predicted time period consisting of a plurality of future time points; the prediction submodule predicts a first prediction track based on the first curvature and the first curvature change rate, and comprises: determining a second curvature of each future point in time based on the first curvature, the first curvature change rate, and preset influence parameters of the first curvature change rate at different points in time, wherein the different points in time comprise the current moment and each future point in time; based on the first curvature and each second curvature, determining coordinates of a plurality of control points corresponding to each prediction time period respectively; and determining a first predicted track by utilizing coordinates of a plurality of control points corresponding to each predicted time period.

In some embodiments, determining the second curvature for each future point in time based on the first curvature, the first curvature rate of change, and the preset influencing parameters of the first curvature rate of change at different points in time, comprises: for each future time point, determining a third curvature of a previous time point of the future time point and preset influence parameters corresponding to different time points; if the previous time point is not the current time point, the second curvature corresponding to the previous time point is the third curvature; obtaining the product of the first curvature change rate and a corresponding preset influence parameter; and determining the addition result of the third curvature and the product, and taking the addition result as the second curvature of the future time point.

In some embodiments, the first motion data acquired by the acquisition module 71 includes a travel speed of the own vehicle at the current time; based on the first curvature and each second curvature, determining coordinates of a plurality of control points corresponding to each predicted time period respectively, including: and determining coordinates of a plurality of control points corresponding to each prediction time period respectively based on the first curvature and each second curvature in response to the running speed being greater than or equal to a preset speed threshold.

In some embodiments, the first motion data acquired by the acquisition module 71 includes a travel speed of the own vehicle at the current time; the second determining module 73 predicts a driving track of the own vehicle in a future preset time period based at least on the first curvature to obtain a first predicted track, including: determining a course angle change amount of the own vehicle based on the shortest safety detection distance and the first curvature in response to the running speed being smaller than a preset speed threshold, wherein the course angle change amount is the course angle change amount of the current position and the end position when the own vehicle runs from the current position to the end position corresponding to the shortest safety detection distance; and determining the positions of a plurality of control points based on the course angle variation and the curvature radius corresponding to the first curvature.

In some embodiments, before the third determination module 74 determines the target detection zone based at least on the first predicted trajectory, it includes: responding to the current frame and the second target tracking vehicle existing in the previous history frame of the current frame, and acquiring second motion data of the second target tracking vehicle relative to the own vehicle at the current moment, wherein the second target tracking vehicle is the first target tracking vehicle in the previous history frame, and the second motion data comprises at least one of position data and an included angle; determining a second predicted track based on the second motion data and the first motion data, the second predicted track characterizing a predicted track of the host vehicle at which the host vehicle travels to the second target tracking vehicle according to the first motion data; determining an object detection region based at least on the first predicted trajectory, comprising: an object detection region is determined based on the first predicted trajectory and the second predicted trajectory.

In some embodiments, the first predicted trajectory includes a number of trajectory points; determining the target detection region based on the first predicted trajectory and the second predicted trajectory, comprising: taking at least part of track segments of the second predicted track as a first detection center line, and respectively determining a first detection boundary line on two sides of the first detection center line based on first preset detection data; determining the ratio of the number of first track points to the number of second track points, wherein the number of the first track points is the number of track points positioned between two first detection boundary lines in the first predicted track, and the number of the second track points is the total number of track points contained in the first predicted track; determining the first predicted track or the second predicted track as a second detection center line based on the ratio; and determining a target detection area based on the second detection center line, the running condition of the own vehicle and corresponding second preset detection data.

In some embodiments, determining the first predicted trajectory or the second predicted trajectory as the second probe centerline based on the ratio comprises one of: determining the first predicted track as a second detection center line in response to the ratio being less than or equal to a preset threshold; and determining the second predicted track as a second detection center line in response to the ratio being greater than a preset threshold.

Referring to fig. 8, fig. 8 is a schematic frame diagram of an embodiment of an electronic device according to the present application. In this embodiment, the electronic device 80 includes a memory 81 and a processor 82 coupled to each other.

The memory 81 stores program instructions for the processor 82 to execute the program instructions stored in the memory 81, the program instructions being executable by the processor to implement the steps of any of the method embodiments described above. In one particular implementation scenario, electronic device 80 may include, but is not limited to: the microcomputer and the server, and the electronic device 80 may also include a mobile device such as a notebook computer and a tablet computer, which is not limited herein.

In particular, the processor 82 is configured to control itself and the memory 81 to implement the steps of any of the embodiments described above. The processor 82 may also be referred to as a CPU (Central Processing Unit ). The processor 82 may be an integrated circuit chip having signal processing capabilities. The processor 82 may also be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a Field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. In addition, the processor 82 may be commonly implemented by an integrated circuit chip.

Referring to fig. 9, fig. 9 is a schematic diagram of a frame of a computer readable storage medium according to the present application. The computer readable storage medium 90 of an embodiment of the present application stores program instructions 91 that when executed implement the method provided by any of the above-described embodiments and any non-conflicting combination. Wherein the program instructions 91 may form a program file stored in the above-mentioned computer readable storage medium 90 in the form of a software product for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned computer-readable storage medium 90 includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes, or a terminal device such as a computer, a server, a mobile phone, a tablet, or the like.

According to the scheme, the first curvature of the vehicle when the vehicle is currently running is determined, the first predicted track of the future preset time period of the vehicle is predicted at least based on the first curvature, and after the target detection area is determined at least based on the first predicted track, the target tracking vehicle is selected according to the determined target detection area. Compared with a mode of determining the first curvature by using the first motion data only, the first curvature determined according to the first motion data, the low-speed calibration value and the high-speed calibration value at the current moment of the vehicle is more accurate, and further after the target detection area is determined at least based on the first curvature, the first target tracking vehicle which is determined by detecting based on the target detection area is more accurate, and particularly in a lane-free scene, the target tracking vehicle can be accurately determined.

In some embodiments, functions or modules included in an apparatus provided by the embodiments of the present disclosure may be used to perform a method described in the foregoing method embodiments, and specific implementations thereof may refer to descriptions of the foregoing method embodiments, which are not repeated herein for brevity.

The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.

In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical, or other forms.

The foregoing description is only of embodiments of the present application, and is not intended to limit the scope of the application, and all equivalent structures or equivalent processes using the descriptions and the drawings of the present application or directly or indirectly applied to other related technical fields are included in the scope of the present application.

Claims

1. A method of selecting a target tracking vehicle, the method comprising:

acquiring first motion data of a vehicle at the current moment; the first motion data at least comprises the running speed of the own vehicle at the current moment;

determining a first curvature of the vehicle when the vehicle is currently running based on the first motion data, the low-speed calibration value and the high-speed calibration value;

predicting the running track of the self-vehicle in a future preset time period based on at least the first curvature to obtain a first predicted track;

determining a target detection area based on at least the first predicted track, and determining a first target tracking vehicle based on detection of the target detection area;

wherein, based on the first motion data, the low-speed calibration value and the high-speed calibration value, determining a first curvature of the vehicle when the vehicle is currently running comprises the following conditions:

Acquiring a first yaw rate of the own vehicle in response to the running speed being less than or equal to the low-speed calibration value, acquiring a first ratio of the first yaw rate to the running speed, and taking the first ratio as a first curvature of the own vehicle;

acquiring a second yaw rate of the own vehicle in response to the running speed being greater than or equal to the high-speed calibration value, acquiring a second ratio of the second yaw rate to the running speed, and taking the second ratio as a first curvature of the own vehicle;

and in response to the running speed being greater than the low-speed calibration value and less than the high-speed calibration value, determining a first weight of the first yaw rate affecting the first curvature and a second weight of the second yaw rate affecting the first curvature, weighting the first yaw rate and the second yaw rate by using the first weight and the second weight to obtain a weighted yaw rate, and acquiring a third ratio of the weighted yaw rate to the running speed as the first curvature of the own vehicle.

2. The method of claim 1, wherein prior to predicting a travel trajectory of the host vehicle for a future preset time period based at least on the first curvature to obtain a first predicted trajectory, the method further comprises:

Determining a first curvature change rate when the vehicle is currently running based on the first motion data, the low-speed calibration value and the high-speed calibration value;

the predicting the running track of the own vehicle in a future preset time period based on at least the first curvature to obtain a first predicted track comprises the following steps:

the first predicted trajectory is predicted based on the first curvature and the first curvature change rate.

3. The method of claim 1, wherein the determining a first weight of the first yaw rate that affects the first curvature and a second weight of the second yaw rate that affects the first curvature comprises:

acquiring a first difference value between the running speed and the low-speed calibration value and a second difference value between the high-speed calibration value and the low-speed calibration value;

acquiring a fourth ratio of the first difference value and the second difference value, and taking the fourth ratio as the second weight;

determining the first weight based on the second weight; wherein the first weight is inversely related to the second weight.

4. The method of claim 2, wherein the first motion data further includes a travel speed of the host vehicle at a current time, a vehicle parameter, and a front wheel angle change amount;

The determining, based on the first motion data, the low-speed calibration value, and the high-speed calibration value, a first curvature change rate when the own vehicle is currently running includes:

determining a yaw acceleration reference value of the own vehicle based on the vehicle parameter and the front wheel-rotation angle variation;

determining a weight-related parameter of yaw acceleration of the own vehicle at the current moment based on the running speed, the low-speed calibration value and the high-speed calibration value, wherein the yaw acceleration is inversely related to the weight-related parameter;

determining the yaw acceleration based on the weight-related parameter and the yaw acceleration reference value;

and obtaining a fifth ratio of the yaw acceleration to the running speed, and taking the fifth ratio as the first curvature change rate.

5. The method according to claim 4, wherein the determining a weight-related parameter of the yaw acceleration of the host vehicle at the current time based on the running speed, the low-speed calibration, and the high-speed calibration includes one of:

determining the weight-related parameter as a first constant in response to the travel speed being less than or equal to the low-speed calibration value;

Determining the weight-related parameter as a second constant in response to the travel speed being greater than or equal to the high-speed calibration value;

in response to the travel speed being greater than the low speed calibration and less than the high speed calibration, obtaining a first difference between the travel speed and the low speed calibration and a second difference between the high speed calibration and the low speed calibration; and obtaining a fourth ratio of the first difference value and the second difference value, and taking the fourth ratio as the weight association parameter.

6. The method of claim 2, wherein the future preset time period comprises a plurality of predicted time periods, each of the predicted time periods consisting of a plurality of future time points;

the predicting the first predicted trajectory based on the first curvature and the first curvature change rate includes:

determining a second curvature for each of the future points in time based on the first curvature, the first curvature change rate, and preset influence parameters of the first curvature change rate at different points in time, the different points in time including the current time and each of the future points in time;

based on the first curvature and the second curvature, determining coordinates of a plurality of control points corresponding to the predicted time periods respectively;

And determining the first predicted track by utilizing the coordinates of the control points corresponding to the predicted time periods respectively.

7. The method of claim 6, wherein the determining the second curvature for each future point in time based on the first curvature, the first curvature rate of change, and the preset influencing parameters of the first curvature rate of change at different points in time comprises:

for each future time point, determining a third curvature of a previous time point of the future time point and preset influence parameters corresponding to different time points; if the previous time point is the current time point, the first curvature is used as the third curvature, and if the previous time point is not the current time point, the second curvature corresponding to the previous time point is the third curvature;

obtaining the product of the first curvature change rate and the corresponding preset influence parameter;

determining a result of addition of the third curvature and the product, and taking the result of addition as the second curvature of the future point in time.

8. The method of claim 7, wherein the first motion data comprises a travel speed of the host vehicle at a current time;

The determining coordinates of a plurality of control points corresponding to each predicted time period based on the first curvature and each second curvature includes:

and determining coordinates of a plurality of control points corresponding to the predicted time periods respectively based on the first curvature and the second curvature in response to the running speed being greater than or equal to a preset speed threshold.

9. The method of claim 1, wherein the first motion data comprises a travel speed of the host vehicle at a current time;

determining a course angle variation of the own vehicle based on the shortest safety detection distance and the first curvature in response to the running speed being smaller than a preset speed threshold, wherein the course angle variation is the course angle variation of the current position and the end position when the own vehicle runs from the current position to the end position corresponding to the shortest safety detection distance;

and determining the positions of a plurality of control points based on the course angle variation and the curvature radius corresponding to the first curvature.

10. The method of claim 1, comprising, prior to said determining a target detection zone based at least on said first predicted trajectory:

responding to a current frame and a second target tracking vehicle existing in a previous history frame of the current frame, and acquiring second motion data of the second target tracking vehicle relative to the own vehicle at the current moment, wherein the second target tracking vehicle is the first target tracking vehicle in the previous history frame, and the second motion data comprises at least one of position data and an included angle;

determining a second predicted trajectory based on the second motion data and the first motion data, the second predicted trajectory characterizing a predicted trajectory at which the host vehicle travels to the second target tracked vehicle in accordance with the first motion data;

the determining the target detection area based at least on the first predicted trajectory includes:

the target detection region is determined based on the first predicted trajectory and the second predicted trajectory.

11. The method of claim 10, wherein the first predicted trajectory comprises a number of trajectory points; the determining the target detection area based on the first predicted trajectory and the second predicted trajectory includes:

Taking at least part of track segments of the second predicted track as a first detection central line, and respectively determining a first detection boundary line on two sides of the first detection central line based on first preset detection data;

determining a ratio of a first track point number to a second track point number, wherein the first track point number is the number of track points between two first detection boundary lines in the first predicted track, and the second track point number is the total number of track points contained in the first predicted track;

determining the first predicted track or the second predicted track as a second detection center line based on the ratio;

and determining the target detection area based on the second detection center line, the running condition of the own vehicle and corresponding second preset detection data.

12. The method of claim 11, wherein the determining, based on the ratio, the first predicted trajectory or the second predicted trajectory as a second probe centerline comprises one of:

determining the first predicted trajectory as the second detection center line in response to the ratio being less than or equal to a preset threshold;

And determining the second predicted track as the second detection center line in response to the ratio being greater than a preset threshold.

13. An electronic device comprising a memory and a processor coupled to each other,

the memory stores program instructions;

the processor is configured to execute program instructions stored in the memory to implement the method of any one of claims 1-12.

14. A computer readable storage medium storing program instructions executable by a processor to implement the method of any one of claims 1-12.