CN117842033A

CN117842033A - Road crossing tracking method based on front vehicle track

Info

Publication number: CN117842033A
Application number: CN202410168304.2A
Authority: CN
Inventors: 周追财
Original assignee: Jika Intelligent Robot Co ltd
Current assignee: Jika Intelligent Robot Co ltd
Priority date: 2024-02-06
Filing date: 2024-02-06
Publication date: 2024-04-09

Abstract

The invention discloses a road crossing tracking method based on a front vehicle track, which is used for determining relative position information of at least one vehicle following object to be screened corresponding to a target vehicle at the current moment when the target vehicle passes through a road crossing, so as to determine the candidate vehicle following object based on the relative position information; determining a current tracking track of the current candidate following object according to the predicted variation of the target vehicle, the current relative position information of the current candidate following object at the current moment and the corresponding historical relative position information aiming at each candidate following object; and determining a target tracking track from the current tracking tracks of the candidate following objects based on a consistency judgment result between the candidate following objects and the historical following objects at the moment which is the last moment of the current moment, so as to control the target vehicle to run based on the target tracking track, and improve the safety and tracking smoothness of the vehicle when the vehicle passes through the lane-free intersection based on an auxiliary driving function.

Description

Road crossing tracking method based on front vehicle track

Technical Field

The embodiment of the invention relates to the technical field of vehicle control, in particular to a road crossing tracking method based on a front vehicle track.

Background

Along with the start of basic auxiliary driving functions widely applied to various car manufacturers at home and abroad, aiming at complex traffic scenes such as disappearance of lane lines when crossing or low confidence of the lane lines, a path planning scheme based on lane line design is difficult to give out a planned path of a vehicle, and at the moment, the application of front car track tracking plays an important role in auxiliary driving of the vehicle.

At present, in the prior art, a single front vehicle track is adopted to control the vehicle to run, however, the track points and the target state information are insensitive, and the like, so that the stability is general under a complex scene of a passing port, and even dangerous situations can occur. The technical problems of low safety and poor vehicle tracking smoothness exist.

Disclosure of Invention

The embodiment of the invention provides a road crossing tracking method based on a front vehicle track, which is used for improving the safety and tracking smoothness of a vehicle when the vehicle passes through a lane-free road crossing based on an auxiliary driving function.

According to a first aspect of the present invention, there is provided a road junction tracking method based on a preceding vehicle track, the method comprising:

when a target vehicle passes through an intersection, determining relative position information of at least one vehicle following object to be screened corresponding to the target vehicle at the current moment, so as to determine a candidate vehicle following object from the at least one vehicle following object to be screened based on the relative position information;

Determining, for each candidate following object, a current tracking track of the current candidate following object based on the predicted variation of the target vehicle, current relative position information of the current candidate following object at the current time and corresponding historical relative position information; the predicted variation is an angle variation, a longitudinal displacement and a transverse displacement of the target vehicle in a period next to the current moment, and the historical relative position information is the relative position information between the current candidate following object and the target vehicle before the current moment;

and determining a target tracking track from the current tracking tracks of the candidate following objects based on a consistency judgment result between the candidate following objects and a historical following object at a moment which is the last time of the current moment, so as to control the target vehicle to run based on the target tracking track.

According to a second aspect of the present invention, there is provided a road junction tracking device based on a preceding vehicle track, the device comprising:

the candidate front vehicle determining module is used for determining relative position information of at least one vehicle following object to be screened corresponding to a target vehicle at the current moment when the target vehicle passes through an intersection, so as to determine candidate vehicle following objects from the at least one vehicle following object to be screened based on the relative position information;

The current track determining module is used for determining the current tracking track of each candidate following object based on the predicted change quantity of the target vehicle, the current relative position information of the current candidate following object at the current moment and the corresponding historical relative position information; the predicted variation is an angle variation, a longitudinal displacement and a transverse displacement of the target vehicle in a period next to the current moment, and the historical relative position information is the relative position information between the current candidate following object and the target vehicle before the current moment;

and the tracking track determining module is used for determining a target tracking track from the current tracking tracks of the candidate car-following objects based on the consistency judgment result between the candidate car-following objects and the historical car-following objects at the moment which is the last time of the current moment so as to control the target vehicle to run based on the target tracking track.

According to a third aspect of the present invention, there is provided an electronic device comprising:

at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores a computer program executable by the at least one processor, so that the at least one processor can execute the road crossing tracking method based on the front vehicle track according to any embodiment of the present invention.

According to a fourth aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the road crossing tracking method based on a preceding vehicle trajectory according to any one of the embodiments of the present invention when executed.

According to the technical scheme, when the target vehicle passes through the intersection, the relative position information of at least one vehicle following object to be screened corresponding to the target vehicle at the current moment is determined, so that the candidate vehicle following object is determined from the at least one vehicle following object to be screened based on the relative position information, and further, for each candidate vehicle following object, the current tracking track of the current candidate vehicle following object is determined based on the predicted change quantity of the target vehicle, the current relative position information of the current candidate vehicle following object at the current moment and the corresponding historical relative position information. The predicted change amount is an angle change amount, a longitudinal displacement amount and a transverse displacement amount of the target vehicle in a period next to the current moment, and the historical relative position information is the relative position information between the current candidate following object and the target vehicle before the current moment. Further, based on consistency judgment results between each candidate following object and the historical following object at the moment previous to the current moment, a target tracking track is determined from the current tracking tracks of each candidate following object, so that the target vehicle is controlled to run based on the target tracking track, and the safety and tracking smoothness of the vehicle are improved when the vehicle passes through the lane-free intersection based on the auxiliary driving function.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a road crossing tracking method based on a preceding vehicle track according to a first embodiment of the present invention;

FIG. 2 is a schematic illustration of displacement of a target vehicle during a time period subsequent to a current time in accordance with a first embodiment of the present invention;

FIG. 3 is a schematic illustration of a candidate car-following object and a historical car-following object according to a first embodiment of the invention;

fig. 4 is a flowchart of a road crossing tracking method based on a track of a preceding vehicle according to a second embodiment of the present invention;

FIG. 5 is a schematic diagram of determining candidate following objects from at least one following object to be screened according to a second embodiment of the invention;

Fig. 6 is a flowchart of a road crossing tracking method based on a preceding vehicle track according to a third embodiment of the present invention;

FIG. 7 is a schematic diagram of determining a current tracking trajectory according to a third aspect of the present invention;

fig. 8 is a schematic structural diagram of a road junction tracking device based on a track of a front vehicle according to a fourth embodiment of the present invention;

fig. 9 is a schematic structural diagram of an electronic device for implementing a road junction tracking method based on a preceding vehicle track according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a road crossing tracking method based on a front vehicle track, which is provided in an embodiment of the present invention, and the embodiment is applicable to a situation that a vehicle is controlled to travel according to a front vehicle travel track when a lane-free intersection is passed through based on an auxiliary driving function. As shown in fig. 1, the method includes:

and S110, when the target vehicle passes through the intersection, determining the relative position information of at least one vehicle following object to be screened corresponding to the target vehicle at the current moment, so as to determine the candidate vehicle following object from the at least one vehicle following object to be screened based on the relative position information.

The target vehicle may be any vehicle that is about to pass through an intersection. The vehicle following object to be screened may be any vehicle located in the vicinity of the target vehicle. The candidate following objects are part of vehicles screened from the plurality of following objects to be screened, and therefore, the candidate following objects belong to the following objects to be screened.

The relative position information comprises a relative transverse distance and a relative longitudinal distance of the vehicle following object to be screened relative to the target vehicle. The relative position information of at least one vehicle following object to be screened can be directly obtained through the network interface.

The intersection may be an intersection with a guidance lane line or an intersection without a guidance lane line. For the intersection with the guide lane line, the technical scheme provided by the embodiment can also be adopted if the confidence of controlling the running of the target vehicle according to the lane line is not ideal.

Specifically, when the target vehicle is detected to pass through the intersection at present, the relative transverse distance and the relative longitudinal distance of at least one vehicle following object to be screened at the present moment are obtained. In order to determine a following object adjacent to the target vehicle position from a plurality of following objects to be screened, a relative transverse distance threshold range or a relative longitudinal distance threshold range may be preset, and the following object to be screened, whose relative transverse distance and relative longitudinal distance are within the relative transverse distance threshold range or the relative longitudinal distance threshold range, may be determined as a candidate following object.

S120, determining the current tracking track of each candidate following object based on the predicted variable quantity of the target vehicle, the current relative position information of the current candidate following object at the current moment and the corresponding historical relative position information.

The predicted variation is an angle variation, a longitudinal displacement and a transverse displacement of the target vehicle in a next time period of the current moment.

In this embodiment, the predicted variation of the target vehicle in the next period of time at the current time is determined, specifically including the following: acquiring the current curvature and the longitudinal speed of a target vehicle; determining the angle change quantity of the target vehicle corresponding to the next predicted time period based on the current curvature, the longitudinal vehicle speed and the preset time length corresponding to the predicted time period; based on the current curvature and the angle change amount, the longitudinal displacement amount and the transverse displacement amount corresponding to the next predicted moment of the target vehicle are determined.

For example, a schematic diagram of the displacement of the target vehicle in a period next to the current time is shown in fig. 2. The angle change amount corresponding to the next predicted time period of the target vehicle is as follows:

Δθ＝Curv×v _x ×Δt (1)

in the formula, v _x For the longitudinal speed at the current moment, deltat is the predicted timeAnd the Curv is the current curvature of the target vehicle for a preset time length corresponding to the segment.

The longitudinal displacement amount of the target vehicle corresponding to the next predicted time period:

the lateral displacement amount of the target vehicle corresponding to the next predicted time period:

in this embodiment, the current relative position information of the current candidate following object is a current relative longitudinal distance and a current relative lateral distance of the current candidate following object with respect to the target vehicle at the current time. The historical relative position information of the current candidate vehicle-following object is the historical relative longitudinal distance and the historical relative transverse distance of the current candidate vehicle-following object relative to the target vehicle before the current moment.

In this embodiment, the specific implementation manner of determining the current tracking track is the same for each candidate following object, and one of the candidate following objects is taken as an example for illustration.

Specifically, firstly, a longitudinal position threshold may be preset, and secondly, a longitudinal deviation distance between a historical moment and a current moment on the current candidate following object is determined based on the historical relative longitudinal distance and the current relative longitudinal distance. Further, the longitudinal deviation distance is numerically compared with the longitudinal position threshold, and there are the following two cases.

First case: if the longitudinal deviation distance is equal to or greater than the longitudinal position threshold, determining a current tracking trajectory of the current candidate following object based on the predicted variation of the target vehicle and the historical relative position information of the current candidate following object. In this case, the determination manner of the current tracking track point corresponding to the current candidate following object is:

wherein ObjPosnLgt (i-1) is the historical relative longitudinal distance, deltax, of the current candidate following object at the last historical moment _Ego For the longitudinal displacement of the target vehicle, objPosnLat (i-1) is the historical relative lateral distance deltay of the current candidate following object at the last historical moment _Ego The delta theta is the angle change quantity corresponding to the next predicted time period of the target vehicle, A (i) is the calculated value of the relative transverse distance of the current tracking track point, and G (i) is the calculated value of the relative longitudinal distance of the current tracking track point.

In particular, if N history periods have elapsed before the current time, N history tracking trajectory points have been generated, and the same translation transformation process needs to be performed on all the N history trajectory points through equation (4).

Second case: if the longitudinal deviation distance is smaller than the longitudinal position threshold value, determining the current tracking track of the current candidate following object based on the predicted variation of the target vehicle and the current relative position information of the current candidate following object. In this case, the determination manner of the current tracking track point corresponding to the current candidate following object is:

wherein, objPosnLgt (i) is the current relative longitudinal distance delta x of the current candidate following object at the current moment _Ego For the longitudinal displacement of the target vehicle, objPosnLat (i) is the current relative lateral distance deltay of the current candidate following object at the current moment _Ego The delta theta is the angle change quantity corresponding to the next predicted time period of the target vehicle, A (i) is the calculated value of the relative transverse distance of the current tracking track point, and G (i) is the calculated value of the relative longitudinal distance of the current tracking track point.

In particular, if N history time periods have elapsed before the current time, N history tracking track points have been generated, and the history tracking track points corresponding to the history time farthest from the current time need to be removed, and the same translation transformation processing is performed on the remaining N-1 history track points through the formula (5).

Based on the above method, a current tracking trajectory for each candidate following object may be determined.

S130, determining a target tracking track from the current tracking tracks of the candidate following objects based on a consistency judgment result between the candidate following objects and the historical following objects at the moment which is the last time of the current moment, so as to control the target vehicle to run based on the target tracking track.

In this embodiment, the candidate following objects include a first candidate following object with the smallest relative longitudinal distance in front of the target vehicle at the current moment and at least one second candidate following object with the relative longitudinal distance within a preset range; the historical vehicle following objects comprise a first historical vehicle following object with the smallest relative longitudinal distance positioned in front of the target vehicle at the moment of the current moment and at least one second historical vehicle following object with the relative longitudinal distance in a preset range.

For example, referring to fig. 3, fig. 3 (a) is a schematic diagram of a position relationship between a target vehicle and a historical following object at a previous time, and fig. 3 (b) is a schematic diagram of a position relationship between a target vehicle and a candidate following object at a current time. Vehicle A1 in fig. 3 (a) is a first historical following object, and vehicles B1 and C1 are second historical following objects; vehicle A2 in fig. 3 (B) is a first candidate following object, and vehicle B2 and vehicle C2 are second candidate following objects.

The consistency determination result refers to whether or not the first candidate following object is consistent with any one of the history following objects. The consistency judgment result mainly comprises: 1. the first candidate following object is consistent with the first historical following object; 2. the first candidate following object is inconsistent with the coding information of the first historical following object, and the coding information of the first historical following object is consistent with the coding information of at least one of the second candidate following objects.

In this embodiment, different consistency determination results, and the target tracking trajectories finally determined are different. Specifically, the method can comprise the following steps:

s1301, if the coding information of the first candidate following object is consistent with that of the first historical following object, determining the current tracking track corresponding to the first candidate following object as a target tracking track.

Wherein the encoded information may be a frame number.

In this embodiment, since the encoded information is different for each vehicle, it is possible to determine whether the same vehicle is one by comparing the encoded information of the vehicles.

For example, referring to fig. 3, if the vehicle A2 coincides with the encoded information of the vehicle A1, the current tracking trajectory of the vehicle A2 is determined as the target tracking trajectory.

S1302, if the coding information of the first candidate following object is inconsistent with the coding information of the first historical following object, and the coding information of the first historical following object is consistent with the coding information of at least one of the second candidate following objects, determining the vehicle with consistent coding information as a to-be-processed following object, so as to determine a target tracking track from the current tracking track corresponding to the first candidate following object and the historical tracking track corresponding to the at least one second historical following object based on the relative position relation among the to-be-processed following object, the first candidate following object and the target vehicle.

Specifically, based on the relative positional relationship among the to-be-processed following object, the first candidate following object and the target vehicle, determining the target tracking track from the current tracking track corresponding to the first candidate following object and the historical tracking track corresponding to the at least one second historical following object may specifically include: respectively determining a first connecting straight line of the to-be-processed following object and the target vehicle and a second connecting straight line of the first candidate following object and the target vehicle; determining a parallelism value based on the included angle value of the first connecting straight line and the second connecting straight line; and determining a target tracking track from the current tracking track corresponding to the first candidate following object and the current tracking track of the following object to be processed based on the parallelism value and the preset parallelism threshold value.

For example, referring to fig. 3, if the encoded information of the vehicle A2 and the encoded information of the vehicle A1 are inconsistent, the encoded information of the vehicle A1 and the encoded information of the vehicle B2 are consistent, or the encoded information of the vehicle A1 and the encoded information of the vehicle C2 are consistent. Assuming that in one specific driving scenario, the encoded information of the vehicle A1 is identical to the encoded information of the vehicle B2, in fig. 3 (B), the vehicle B2 is the object to be processed for following. Further, the center point of the rear axle of the vehicle may be used as a reference point to connect the reference point of the target vehicle with the reference point of the vehicle A2, thereby obtaining a first connecting line; connecting the reference point of the target vehicle with the reference point of the vehicle B2 to obtain a second connecting straight line; determining an included angle value of the first connecting straight line and the second connecting straight line as a parallelism value to be compared; if the parallelism value to be compared is smaller than a preset parallelism threshold value, determining the current tracking track corresponding to the first candidate vehicle-following object as a target tracking track; and if the parallelism value to be compared is greater than or equal to a preset parallelism threshold value, determining a target tracking track from the current tracking tracks of the vehicle following objects to be processed.

On the basis of obtaining the target tracking track, the target vehicle is driven along the target tracking track by adjusting the movement control parameters of the target vehicle. And then, updating the next moment of the current moment to the current moment, and repeating the steps of determining the candidate following object of the target vehicle at the current moment, determining the current tracking track corresponding to the candidate following object and determining the target tracking track based on the current tracking track until the target vehicle passes through the intersection.

On the basis of the embodiment, on the basis of obtaining the current tracking track of each candidate following object, the current tracking track of each candidate following object is stored, so that when the candidate following object determined at the next moment of the current moment comprises the candidate following object at the current moment, the current tracking track of the candidate following object is called as the historical tracking track, and because the historical tracking track is directly called, the processing time of track planning can be reduced without re-planning.

Particularly, if any one vehicle following object to be screened cannot be determined at the next moment of the current moment, the target vehicle is still controlled to run according to the target tracking track at the current moment.

Example two

Fig. 4 is a flowchart of a road junction tracking method based on a preceding vehicle track according to a second embodiment of the present invention, and S110 is further refined based on the foregoing embodiment. Wherein, the technical terms identical to or corresponding to the above embodiments are not repeated herein.

As shown in fig. 4, the method includes:

s210, when the target vehicle passes through the intersection, determining the relative position information of at least one vehicle following object to be screened corresponding to the target vehicle at the current moment, and determining the initial curvature of the target vehicle.

Specifically, determining the initial curvature of the target vehicle specifically includes:

acquiring the current running speed, the current yaw rate and the current longitudinal speed of a target vehicle;

if the current running speed is greater than the first threshold value, determining the initial curvature of the target vehicle based on the current yaw rate and the current longitudinal speed of the target vehicle;

if the current running speed is smaller than the second threshold value, determining the initial curvature of the target vehicle based on a calculation mode of a two-degree-of-freedom model of the vehicle;

if the current running speed is between the first threshold value and the second threshold value, determining a first initial curvature based on the current yaw rate and the current longitudinal speed of the target vehicle, determining a second initial curvature based on a calculation mode of a two-degree-of-freedom model of the vehicle, and determining an initial curvature of the target vehicle based on a weighted sum of the first initial curvature and the second initial curvature.

In the present embodiment, the current running speed, the current yaw rate, and the current longitudinal vehicle speed are all directly available amounts. The first threshold and the second threshold are preset speed thresholds. For example, the first threshold is 5m/s and the second threshold is 3m/s.

Among them, the two-degree-of-freedom Model of the vehicle is (Linear 2DOF Model) which is an important Model in the field of vehicle dynamics and is used for describing the motion characteristics of the vehicle in a plane. The two-degree-of-freedom model of the vehicle is based on the following two assumptions: 1) The motion of the vehicle is in-plane; 2) The vehicle receives only two control inputs, vehicle speed and front wheel steering angle. Based on this model, the initial curvature of the target vehicle can be deduced in combination with the prior art.

On the above exemplary basis, if the current running speed is greater than 5m/s, the initial curvature of the target vehicle is:

wherein yawrate is the current yaw rate of the target vehicle, v _x A current longitudinal vehicle speed that is a target vehicle;

if the current running speed is less than 3m/s, determining the initial curvature of the target vehicle based on a calculation mode of a two-degree-of-freedom model of the vehicle;

if the current running speed is between 3m/s and 5m/s, determining based on the current yaw rate of the target vehicle and the current longitudinal vehicle speed Determination of Q based on calculation mode of two-degree-of-freedom model of vehicle ₂ The initial curvature of the target vehicle is q=α ₁ Q ₁ +α ₂ Q ₂ Wherein alpha is ₁ And alpha ₂ Is a preset weight value.

S220, for each car following object to be screened, determining a predicted track fitting curve of the target vehicle based on the course angle and the initial curvature of the target vehicle.

In this embodiment, for each vehicle following object to be screened, assuming that the orientation angle at the end point of the predicted track of the target vehicle is consistent with the vehicle following object to be screened, and the predicted track fitting curve of the target vehicle is a clothoid curve, the predicted track fitting curve may be expressed as:

where y is the lateral distance and x is the longitudinal distance.

Further, the key to solving the predicted trajectory fitting curve is to determine c ₀ 、c ₁ 、c ₂ C ₃ 。

c ₀ For the relative transverse distance, c, of the following objects to be screened ₁ Is tan (AgDir), wherein AgDir is the course angle, c of the following object to be screened ₂ Is the initial curvature of the target vehicle.

Next, c is determined ₃ . It is emphasized that in the course of the subsequent derivation, the AgDir is used in the opposite sense, and in addition, c ₂ Multiplied by 2. The purpose of the derivation is herein to obtain a pre-predictionAnd (3) measuring the shortest transverse distance between the track fitting curve and the vehicle-following object to be screened, so that the derivative of y is 0, and deriving the formula (7) to obtain:

And S230, determining the lateral deviation distance between the predicted end point of the predicted track fitting curve and the vehicle following object to be screened based on the predicted track fitting curve, the relative lateral distance and the relative longitudinal distance.

In this embodiment, the relative lateral distance and the relative longitudinal distance of the vehicle-following object to be screened are brought into the predicted track fitting curve, and the lateral deviation distance between the predicted end point of the predicted track fitting curve and the vehicle-following object to be screened obtained may be expressed as follows:

where obj posnlat is the relative lateral distance of the object to be screened and obj posnlgt is the relative longitudinal distance of the object to be screened.

S240, determining candidate car-following objects from the at least one car-following object to be screened based on the corresponding lateral deviation distance of the car-following objects to be screened and preset screening conditions.

Wherein, the preset screening condition is a preset transverse deviation threshold range.

In this embodiment, through steps S220 and S230, a lateral deviation distance corresponding to each vehicle following object to be screened may be obtained, so that the vehicle following object to be screened whose lateral deviation distance is within a lateral deviation threshold range is determined as a candidate vehicle following object.

For example, referring to fig. 5, a schematic diagram of determining candidate following objects from at least one following object to be screened, the lateral deviation threshold range may include a left area, a ego area, and a right area, and the calculated lateral deviation distance is put into a funnel model, and two candidate following objects closest to the target vehicle in front are screened out, one candidate following object closest to the target vehicle in the left area, and one candidate following object closest to the target vehicle in the right area.

S250, determining the current tracking track of each candidate following object based on the predicted change quantity of the target vehicle, the current relative position information of the current candidate following object at the current moment and the corresponding historical relative position information.

S260, determining a target tracking track from the current tracking tracks of the candidate following objects based on a consistency judgment result between the candidate following objects and the historical following objects at the moment which is the last time of the current moment, so as to control the target vehicle to run based on the target tracking track.

According to the technical scheme, when candidate car following objects are determined from at least one car following object to be screened, a predicted track fitting curve of a target vehicle is determined for each car following object to be screened based on a course angle and the initial curvature of the target vehicle; determining the lateral deviation distance between a predicted end point of the predicted track fitting curve and a vehicle-following object to be screened based on the predicted track fitting curve, the relative lateral distance and the relative longitudinal distance; and determining candidate car-following objects from at least one car-following object to be screened based on the corresponding transverse deviation distance of each car-following object to be screened and a preset screening condition. According to the method, the device and the system, the lateral deviation distance between the predicted end point of the predicted track fitting curve of the target vehicle and the vehicle following object to be screened is used as the screening index, and the target vehicle with better tracking effect can be screened out by considering the predicted track of the target vehicle when the candidate vehicle following object is determined as the target vehicle is in a moving state in the process of passing through the road.

Example III

Fig. 6 is a flowchart of a road junction tracking method based on a preceding vehicle track according to a third embodiment of the present invention, and S120 is further refined based on the foregoing embodiment. Wherein, the technical terms identical to or corresponding to the above embodiments are not repeated herein.

As shown in fig. 6, the method includes:

and S310, when the target vehicle passes through the intersection, determining the relative position information of at least one vehicle following object to be screened corresponding to the target vehicle at the current moment, so as to determine the candidate vehicle following object from the at least one vehicle following object to be screened based on the relative position information.

S320, for each candidate car-following object, determining the longitudinal deviation distance between a historical moment and the current moment on the basis of the historical relative longitudinal distance and the current relative longitudinal distance.

In this embodiment, one of the candidate following objects is taken as the current candidate following object. The current relative position information of the current candidate vehicle-following object comprises a current relative longitudinal distance and a current relative lateral distance, and the historical relative position information of the current candidate vehicle-following object comprises a historical relative longitudinal distance and a historical relative lateral distance.

If the historical relative longitudinal distance is ObjPosnLgt (i-1), the current relative longitudinal distance is ObjPosnLgt (i), and the longitudinal deviation distance between the last historical moment and the current moment of the current candidate following object is:

Lgt＝ObjPosnLgt(i)-ObjPosnLgt(i-1)(12)

s330, determining a longitudinal position threshold corresponding to the current relative longitudinal distance.

In this embodiment, a specific implementation manner of determining the longitudinal position threshold corresponding to the current relative longitudinal distance is: determining a first comparison value based on the current relative longitudinal distance and a first preset value; determining the maximum value of the first comparison value and the second preset value as a second comparison value; a longitudinal position threshold is determined based on the minimum of the second comparison value and the third preset value.

The first preset value is a total number of preset track points corresponding to the tracking track, for example, the first preset value is 30; the second preset value is 1; the third preset value is a preset longitudinal position limit value, for example, the third preset is a value of 5.

On the above exemplary basis, determining a longitudinal position threshold corresponding to the current relative longitudinal distance may be formulated as:

ΔObjPosnLgt＝min(5,max(1,ObjPosnLgt(i)/30)) (13)

wherein Δobj posnlgt is a longitudinal position threshold, objPosnLgt (i) is a current relative longitudinal distance, 30 is a first preset value, 1 is a second preset value, and 5 is a third preset value.

In a specific application, the current relative longitudinal distance is taken into equation (13), and the longitudinal position threshold is obtained.

S340, judging whether the longitudinal deviation distance is larger than or equal to the longitudinal position threshold value.

In this embodiment, the magnitude relation between the longitudinal deviation distance and the longitudinal position threshold is compared on the basis of the obtained longitudinal deviation distance and the longitudinal position threshold, and if the longitudinal deviation distance is equal to or greater than the longitudinal position threshold, S351 is executed, and if the longitudinal deviation distance is less than the longitudinal position threshold, S352 is executed.

S351, if yes, determining a target newly-increased track point based on the predicted change quantity of the target vehicle and the historical relative position information of the current candidate vehicle-following object, and determining the current tracking track of the current candidate vehicle-following object based on the target newly-increased track point.

It should be noted that, if N history periods have elapsed before the current time, N history tracking track points have been generated, and the N history tracking track points are a history track point queue.

Wherein the newly added track points of the target are the track points which are newly added except the history track point queue. For example, the history track point queue already includes 20 history track points, and the newly added track point of the target is the 21 st track point.

In this embodiment, in this case, the determination manner of the target newly added track point corresponding to the current candidate following object is:

wherein ObjPosnLgt (i-1) is the historical relative longitudinal distance, deltax, of the current candidate following object at the last historical moment _Ego For the longitudinal displacement of the target vehicle, objPosnLat (i-1) is the historical relative lateral distance deltay of the current candidate following object at the last historical moment _Ego The delta theta is the angle change amount of the target vehicle corresponding to the next predicted time period, A (i) is the calculated value of the relative transverse distance of the target newly-added track point, and G (i) is the calculated value of the relative longitudinal distance of the target newly-added track point.

Further, determining the current tracking track of the current candidate following object based on the newly added track point of the target specifically includes: acquiring a history track point queue of a current candidate vehicle following object; adding the target newly-added track points into the historical track point queue, and updating the numerical value of each historical track point in the historical track point queue based on the target newly-added track points.

For example, the history track point queue already includes 20 history track points, the target newly added track point is added to the history track point queue, and the current track includes 21 track points. Meanwhile, the same translation transformation processing is performed on all 20 history track points through the formula (14).

And S352, if not, determining a track point to be updated based on the predicted change amount of the target vehicle and the current relative position information of the current candidate following object, and determining the current tracking track of the current candidate following object based on the track point to be updated.

Further, determining the current tracking track of the current candidate following object based on the track point to be updated may specifically include: acquiring a history track point queue of a current candidate vehicle following object; determining a historical track point corresponding to the historical moment farthest from the current moment in the historical track point queue as a first historical track point, and determining the rest historical track points in the historical track queue as second historical track points; rejecting the first historical track point; numerical value updating is carried out on each second historical track point based on the track points to be updated, so that second updated historical track points are obtained; and forming the current tracking track of the current candidate following object based on the track points to be updated and the second updated historical track points.

In this embodiment, in this case, the determination manner of the track point to be updated corresponding to the current candidate following object is:

wherein, objPosnLgt (i) is the current relative longitudinal distance delta x of the current candidate following object at the current moment _Ego For the longitudinal displacement of the target vehicle, objPosnLat (i) is the current relative lateral distance deltay of the current candidate following object at the current moment _Ego For the lateral displacement of the target vehicle, Δθ is the angle change corresponding to the target vehicle in the next predicted time period, a (i) is the calculated value of the relative lateral distance of the track point to be updated, and G (i) is the calculated value of the relative longitudinal distance of the track point to be updated.

For example, referring to fig. 7, the history track point queue includes 10 history track points, which are A, B, C, D, E, F, G, H, I, J respectively, the history moments corresponding to the 10 history track points are t1, t2, t3, t4, t5, t6, t7, t8, t9 and t10 respectively, t11 in the drawing is the current moment, t10 is closest to the current moment t11, t1 is the first history track point when t1 is farthest from the current moment t11, the history track point a is the second history track point, the history track point B, C, D, E, F, G, H, I, J is the second history track point, the history track point a corresponding to t1 is removed, the history track points B, C, D, E, F, G, H, I, J are all subjected to the same translation transformation processing through the formula (15) to obtain second updated history track points B1, C1, D1, E1, F1, G1, H1, I1, J1, S in fig. 7 represents track points to be updated, and 10 track points, such as S, B, C1, D1, E1, F1, H1, I1 and J1, form a current track candidate track point.

It should be noted that, on the basis of obtaining the current tracking track corresponding to each candidate following object, each track point in the current tracking track is removed, so as to ensure that the track point farthest from the current tracking track is closer to the target vehicle. In addition, filtering and slope limiting processes are performed on the current tracking trajectory.

S360, determining a target tracking track from the current tracking tracks of the candidate following objects based on a consistency judgment result between the candidate following objects and the historical following objects at the moment which is the last time of the current moment, so as to control the target vehicle to run based on the target tracking track.

When determining the current tracking track of the current candidate following object, firstly, determining the longitudinal deviation distance between the last historical moment of the current candidate following object and the current moment based on the historical relative longitudinal distance and the current relative longitudinal distance; determining a longitudinal position threshold based on the current relative longitudinal distance and a preset threshold determining function; if the longitudinal deviation distance is greater than or equal to the longitudinal position threshold value, determining a target newly-increased track point based on the predicted variable quantity of the target vehicle and the historical relative position information of the current candidate vehicle-following object, and determining the current tracking track of the current candidate vehicle-following object based on the target newly-increased track point; if the longitudinal deviation distance is smaller than the longitudinal position threshold value, determining a track point to be updated based on the predicted variation of the target vehicle and the current relative position information of the current candidate vehicle-following object, and determining the current tracking track of the current candidate vehicle-following object based on the track point to be updated. In this embodiment, the magnitude relation between the longitudinal deviation distance and the longitudinal position threshold of the current candidate tracking object is compared, and different current tracking track determining modes are corresponding to different comparison results, if the longitudinal deviation distance is too large, in order to avoid that the displacement amplitude of the current tracking track is too large, the historical relative position information of the current candidate tracking object is used as an input parameter to determine a new track point of the target, the obtained current tracking track is not changed too much, and further, the safety and tracking smoothness of the vehicle are improved when the vehicle passes through the lane-free intersection based on the auxiliary driving function.

Example IV

Fig. 8 is a schematic structural diagram of a road junction tracking device based on a track of a front vehicle according to a fourth embodiment of the present invention. As shown in fig. 8, the apparatus includes: the candidate lead determination module 410, the current trajectory determination module 420, and the tracking trajectory determination module 430.

The candidate front vehicle determining module 410 is configured to determine, when a target vehicle passes through an intersection, relative position information of at least one vehicle following object to be screened corresponding to the target vehicle at a current moment, so as to determine a candidate vehicle following object from the at least one vehicle following object to be screened based on each piece of relative position information;

the current track determining module 420 is configured to determine, for each candidate following object, a current tracking track of the current candidate following object based on the predicted variation of the target vehicle, the current relative position information of the current candidate following object at the current moment, and the corresponding historical relative position information; the predicted variation is an angle variation, a longitudinal displacement and a transverse displacement of the target vehicle in a period next to the current moment, and the historical relative position information is the relative position information between the current candidate following object and the target vehicle before the current moment;

The tracking track determining module 430 is configured to determine a target tracking track from the current tracking tracks of the candidate following objects based on a consistency determination result between each candidate following object and a historical following object at a time previous to the current time, so as to control the target vehicle to travel based on the target tracking track.

Optionally, the road crossing tracking device based on the track of the preceding vehicle further comprises: the current track storage module is used for specifically storing the current tracking track of the candidate car-following object so as to call the current tracking track of the candidate car-following object as a historical tracking track when the candidate car-following object at the current moment is included in the candidate car-following object determined at the next moment of the current moment.

Optionally, the road crossing tracking device based on the track of the preceding vehicle further comprises: and the repeated execution module is specifically configured to update the next time of the current time to the current time, and repeatedly execute the steps of determining a candidate vehicle following object of the target vehicle at the current time, determining a current tracking track corresponding to the candidate vehicle following object, and determining a target tracking track based on the current tracking track until the target vehicle passes through the intersection.

Optionally, the relative position information includes a heading angle, a relative lateral distance, and a relative longitudinal distance, and the candidate front vehicle determining module 410 includes:

an initial curvature determination unit configured to determine an initial curvature of the target vehicle;

a predicted track determining unit, configured to determine, for each of the objects to be screened, a predicted track fitting curve of the target vehicle based on the heading angle and an initial curvature of the target vehicle;

The transverse deviation determining unit is used for determining the transverse deviation distance between the predicted end point of the predicted track fitting curve and the object to be screened following the vehicle based on the predicted track fitting curve, the relative transverse distance and the relative longitudinal distance;

and the candidate car-following object determining unit is used for determining the candidate car-following object from the at least one car-following object to be screened based on the transverse deviation distance corresponding to each car-following object to be screened and the preset screening condition.

Optionally, the initial curvature determining unit includes:

the vehicle current information acquisition subunit is used for acquiring the current running speed, the current yaw rate and the current longitudinal vehicle speed of the target vehicle;

a first determining subunit, configured to determine an initial curvature of the target vehicle based on a current yaw rate and a current longitudinal vehicle speed of the target vehicle if the current running speed is greater than a first threshold;

a second determining subunit, configured to determine, if the current running speed is less than a second threshold, an initial curvature of the target vehicle based on a calculation mode of a two-degree-of-freedom model of the vehicle;

and a third determining subunit, configured to determine a first initial curvature based on a current yaw rate and a current longitudinal vehicle speed of the target vehicle, determine a second initial curvature based on the calculation method based on the two-degree-of-freedom model of the vehicle, and determine an initial curvature of the target vehicle based on a weighted sum of the first initial curvature and the second initial curvature if the current running speed is between the first threshold and the second threshold.

Optionally, the current relative position information includes a current relative longitudinal distance and a current relative lateral distance, the historical relative position information includes a historical relative longitudinal distance and a historical relative lateral distance, and the current track determining module 420 includes:

a longitudinal deviation determining unit, configured to determine a longitudinal deviation distance between a historical moment and a current moment on the current candidate following object based on the historical relative longitudinal distance and the current relative longitudinal distance;

a longitudinal threshold determining unit configured to determine a longitudinal position threshold corresponding to the current relative longitudinal distance;

a track first determining unit, configured to determine a target newly-added track point based on a predicted variation of the target vehicle and historical relative position information of the current candidate following object if the longitudinal deviation distance is greater than or equal to the longitudinal position threshold, and determine a current tracking track of the current candidate following object based on the target newly-added track point;

a track second determining unit, configured to determine a track point to be updated based on the predicted variation of the target vehicle and the current relative position information of the current candidate following object if the longitudinal deviation distance is smaller than the longitudinal position threshold, and determine a current tracking track of the current candidate following object based on the track point to be updated;

The longitudinal threshold determining unit is specifically configured to determine a first comparison value based on the current relative longitudinal distance and a first preset value; the first preset value is the maximum value of the first comparison value and the second preset value, and the maximum value is determined to be the second comparison value, wherein the total number of the preset track points corresponding to the tracking track; wherein the second preset value is 1; determining a longitudinal position threshold based on the minimum of the second comparison value and the third preset value; wherein the third preset value is a preset longitudinal position limit value.

Optionally, the track first determining unit further includes: the track point new adding subunit is specifically configured to obtain a history track point queue of the current candidate following object; and adding the target newly-added track point into a history track point queue, and updating the numerical value of each history track point in the history track point queue based on the target newly-added track point.

Optionally, the track second determining unit further includes: the track point replacing subunit is specifically used for acquiring a history track point queue of the current candidate following object; determining a historical track point corresponding to the historical moment farthest from the current moment in the historical track point queue as a first historical track point, and determining the rest historical track points in the historical track queue as second historical track points; rejecting the first historical track point; numerical value updating is carried out on each second historical track point based on the track points to be updated, so that second updated historical track points are obtained; and forming the current tracking track of the current candidate following object based on the track points to be updated and the second updated historical track points.

Optionally, the candidate following objects include a first candidate following object whose relative longitudinal distance is the smallest and at least one second candidate following object whose relative longitudinal distance is within a preset range, the first candidate following object whose relative longitudinal distance is the smallest and at least one second candidate following object whose relative longitudinal distance is the smallest and which is located in front of the target vehicle at the previous time, and the tracking track determining module 430 includes:

the tracking track first determining unit is used for determining the current tracking track corresponding to the first candidate following object as a target tracking track if the coding information of the first candidate following object is consistent with the coding information of the first historical following object;

and the tracking track second determining unit is used for determining the second candidate following object with consistent coding information as the following object to be processed if the coding information of the first candidate following object is inconsistent with the coding information of the first historical following object and the coding information of at least one of the second candidate following objects is consistent with the coding information of the first historical following object, so as to determine the target tracking track from the current tracking track corresponding to the first candidate following object and the current tracking track of the following object to be processed based on the relative position relation among the following object to be processed, the first candidate following object and the target vehicle.

Optionally, the second tracking track determining unit is specifically further configured to determine a first connection line between the to-be-processed following object and the target vehicle, and a second connection line between the first candidate following object and the target vehicle, respectively; determining a parallelism value to be compared based on the included angle value of the first connecting straight line and the second connecting straight line; and determining a target tracking track from the current tracking track corresponding to the first candidate following object and the current tracking track of the following object to be processed based on the parallelism value to be compared and a preset parallelism threshold value.

The road crossing tracking device based on the front vehicle track provided by the embodiment of the invention can execute the road crossing tracking method based on the front vehicle track provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example five

Fig. 9 shows a schematic diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 9, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a road crossing tracking method based on a preceding vehicle trajectory.

In some embodiments, the approach path tracking method based on the lead track may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the road junction tracking method based on a preceding vehicle trajectory described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the approach path tracking method based on the lead track in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. The road crossing tracking method based on the track of the front vehicle is characterized by comprising the following steps of:

2. The method according to claim 1, wherein the method further comprises:

and storing the current tracking track of the candidate car-following object so as to call the current tracking track of the candidate car-following object as a historical tracking track when the candidate car-following object at the current moment is included in the candidate car-following object determined at the next moment of the current moment.

3. The method according to claim 1, characterized in that after said controlling the target vehicle to travel based on the target tracking trajectory, the method further comprises:

and updating the next moment of the current moment to the current moment, and repeating the steps of determining the candidate vehicle-following object of the target vehicle at the current moment, determining the current tracking track corresponding to the candidate vehicle-following object and determining the target tracking track based on the current tracking track until the target vehicle passes through the intersection.

4. The method of claim 1, wherein the relative position information includes a heading angle, a relative lateral distance, and a relative longitudinal distance, and wherein determining a candidate car-following object from the at least one car-following object to be screened based on each of the relative position information comprises:

determining an initial curvature of the target vehicle;

determining a predicted track fitting curve of the target vehicle based on the course angle and the initial curvature of the target vehicle for each vehicle following object to be screened;

determining the lateral deviation distance between a predicted end point of the predicted track fitting curve and a vehicle-following object to be screened based on the predicted track fitting curve, the relative lateral distance and the relative longitudinal distance;

and determining candidate car following objects from the at least one car following object to be screened based on the corresponding transverse deviation distance of the car following objects to be screened and a preset screening condition.

5. The method of claim 4, wherein the determining an initial curvature of the target vehicle comprises:

acquiring the current running speed, the current yaw rate and the current longitudinal speed of the target vehicle;

if the current running speed is greater than a first threshold value, determining the initial curvature of the target vehicle based on the current yaw rate and the current longitudinal vehicle speed of the target vehicle;

If the current running speed is smaller than a second threshold value, determining the initial curvature of the target vehicle based on a calculation mode of a two-degree-of-freedom model of the vehicle;

and if the current running speed is between the first threshold value and the second threshold value, determining a first initial curvature based on the current yaw rate and the current longitudinal speed of the target vehicle, determining a second initial curvature based on the calculation mode based on the two-degree-of-freedom model of the vehicle, and determining the initial curvature of the target vehicle based on the weighted sum of the first initial curvature and the second initial curvature.

6. The method of claim 1, wherein the current relative position information includes a current relative longitudinal distance and a current relative lateral distance, the historical relative position information includes a historical relative longitudinal distance and a historical relative lateral distance, the determining the current tracking trajectory of the current candidate following object based on the predicted amount of change of the target vehicle, the current relative position information of the current candidate following object at the current time, and the corresponding historical relative position information includes:

determining a longitudinal deviation distance between a historical moment and a current moment of the current candidate vehicle-following object based on the historical relative longitudinal distance and the current relative longitudinal distance;

Determining a longitudinal position threshold corresponding to the current relative longitudinal distance;

if the longitudinal deviation distance is greater than or equal to the longitudinal position threshold, determining a target newly-increased track point based on the predicted variation of the target vehicle and the historical relative position information of the current candidate following object, and determining the current tracking track of the current candidate following object based on the target newly-increased track point;

if the longitudinal deviation distance is smaller than the longitudinal position threshold, determining a track point to be updated based on the predicted variation of the target vehicle and the current relative position information of the current candidate following object, and determining the current tracking track of the current candidate following object based on the track point to be updated;

wherein said determining a longitudinal position threshold corresponding to said current relative longitudinal distance comprises:

determining a first comparison value based on the current relative longitudinal distance and a first preset value; wherein the first preset value is the total number of preset track points corresponding to the tracking track

Determining the maximum value of the first comparison value and the second preset value as a second comparison value; wherein the second preset value is 1;

Determining a longitudinal position threshold based on the minimum value of the second comparison value and a third preset value; wherein the third preset value is a preset longitudinal position limit value.

7. The method of claim 6, wherein the determining the current tracking trajectory of the current candidate following object based on the target newly added trajectory point comprises:

acquiring a history track point queue of the current candidate vehicle-following object;

and adding the target newly-added track point into a history track point queue, and updating the numerical value of each history track point in the history track point queue based on the target newly-added track point.

8. The method of claim 6, wherein the determining the current tracking trajectory of the current candidate following object based on the trajectory point to be updated comprises:

acquiring a history track point queue of a current candidate vehicle following object;

determining a historical track point corresponding to the historical moment farthest from the current moment in the historical track point queue as a first historical track point, and determining the rest historical track points in the historical track queue as second historical track points;

rejecting the first historical track point;

Numerical value updating is carried out on each second historical track point based on the track points to be updated, so that second updated historical track points are obtained;

and forming the current tracking track of the current candidate following object based on the track points to be updated and the second updated historical track points.

9. The method of claim 1, wherein the candidate following objects include a first candidate following object whose relative longitudinal distance is the smallest and at least one second candidate following object whose relative longitudinal distance is within a preset range that are located in front of the target vehicle at a current time, the history following object includes a first history following object whose relative longitudinal distance is the smallest that is located in front of the target vehicle at a time that is the last of the current time and at least one second history following object whose relative longitudinal distance is within a preset range, the determining a target tracking trajectory from the current tracking trajectories of the candidate following objects based on a result of a consistency determination between the candidate following objects and the history following object that is the last of the current time, comprising:

if the first candidate following object is consistent with the coding information of the first historical following object, determining the current tracking track corresponding to the first candidate following object as a target tracking track;

And if the coding information of the first candidate following object is inconsistent with the coding information of the first historical following object, and the coding information of the first historical following object is consistent with the coding information of at least one of the second candidate following objects, determining the second candidate following object with consistent coding information as a to-be-processed following object, so as to determine a target tracking track from the current tracking track corresponding to the first candidate following object and the current tracking track of the to-be-processed following object based on the relative position relation among the to-be-processed following object, the first candidate following object and the target vehicle.

10. The method of claim 9, wherein the determining a target tracking trajectory from a current tracking trajectory corresponding to the first candidate following object and a current tracking trajectory of the to-be-processed following object based on the relative positional relationship of the to-be-processed following object, the first candidate following object, and the target vehicle comprises:

determining a first connecting straight line of the to-be-processed following object and the target vehicle and a second connecting straight line of the first candidate following object and the target vehicle respectively;

Determining a parallelism value to be compared based on the included angle value of the first connecting straight line and the second connecting straight line;

and determining a target tracking track from the current tracking track corresponding to the first candidate following object and the current tracking track of the following object to be processed based on the parallelism value to be compared and a preset parallelism threshold value.