CN114643988B - Tracking target determination method and device, electronic equipment and storage medium - Google Patents

Tracking target determination method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN114643988B
CN114643988B CN202210548956.XA CN202210548956A CN114643988B CN 114643988 B CN114643988 B CN 114643988B CN 202210548956 A CN202210548956 A CN 202210548956A CN 114643988 B CN114643988 B CN 114643988B
Authority
CN
China
Prior art keywords
vehicle
obstacle
offset
lane
self
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210548956.XA
Other languages
Chinese (zh)
Other versions
CN114643988A (en
Inventor
郭守昌
董健
林志华
江鑫豪
成伟
陆佳辉
武静雯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Hongjing Zhijia Technology Co ltd
Original Assignee
Hangzhou Hongjing Zhijia Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Hongjing Zhijia Technology Co ltd filed Critical Hangzhou Hongjing Zhijia Technology Co ltd
Priority to CN202210548956.XA priority Critical patent/CN114643988B/en
Publication of CN114643988A publication Critical patent/CN114643988A/en
Application granted granted Critical
Publication of CN114643988B publication Critical patent/CN114643988B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/14—Adaptive cruise control
    • B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
    • B60W30/165—Automatically following the path of a preceding lead vehicle, e.g. "electronic tow-bar"
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0025—Planning or execution of driving tasks specially adapted for specific operations
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to a tracking target determination method and device, an electronic device and a computer-readable storage medium. The method comprises the following steps: obtaining obstacle vehicle information by a vehicle-mounted radar or a vehicle-mounted camera; determining the running track of the vehicle; determining an obstacle screening boundary based on the driving track of the vehicle; determining the offset degree of the obstacle vehicle relative to the vehicle according to the obstacle vehicle information; and determining the obstacle vehicle to be tracked according to the deviation degree and the obstacle screening boundary. The method can effectively reduce the wrong selection of the following target and improve the accuracy of the selection of the following target, thereby improving the self-adaptive cruise control of automatic driving.

Description

Tracking target determination method and device, electronic equipment and storage medium
Technical Field
The present invention relates to an automatic driving technique.
Background
The self-adaptive cruise control is a basic function in automatic driving, the first consideration for realizing the self-adaptive cruise is to select a proper vehicle following target, and the accuracy of the selection of the vehicle following target directly determines whether the self-adaptive cruise system can achieve the expected effect on the driving control of the vehicle. At present, the problem of mistaken selection of a vehicle following target exists in target selection of adaptive cruise.
Disclosure of Invention
The present invention has been made keeping in mind the above problems occurring in the prior art, and is intended to solve one or more of the problems occurring in the prior art.
According to an aspect of the present invention, there is provided a tracking target determining method, including: obtaining obstacle vehicle information by a vehicle-mounted radar or a vehicle-mounted camera; determining the running track of the vehicle; determining an obstacle screening boundary based on the driving track of the vehicle; determining the offset degree of the obstacle vehicle relative to the vehicle according to the obstacle vehicle information; and determining the obstacle vehicle to be tracked according to the deviation degree and the obstacle screening boundary.
According to another aspect of the present invention, there is provided a tracking target determining apparatus including: an obstacle vehicle information obtaining unit that obtains obstacle vehicle information from a vehicle-mounted radar or a vehicle-mounted camera; a self vehicle running track determining unit for determining a self vehicle running track; an obstacle screening boundary determination unit for determining an obstacle screening boundary based on a running track of the own vehicle; the obstacle vehicle offset degree determining unit is used for determining the offset degree of the obstacle vehicle relative to the vehicle according to the obstacle vehicle information; and a tracked vehicle determining unit which determines the obstacle vehicle to be tracked according to the deviation degree and the obstacle screening boundary.
According to another aspect of the present invention, there is provided an electronic apparatus comprising: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method of the present invention.
According to still another aspect of the present invention, there is provided a computer-readable storage medium on which a device control program is stored, which when executed by a processor, implements the method of the present invention.
Drawings
The invention may be better understood with reference to the following drawings. The drawings are only schematic and are non-limiting of the scope of the invention. The figures are not drawn to scale.
Fig. 1 is a schematic flow chart illustrating a tracking target determining method according to an embodiment of the present invention.
Fig. 2 illustrates an obstacle screening boundary determined in accordance with one embodiment of the present invention.
Fig. 3A to 3C are diagrams illustrating determination of the degree of offset of an obstacle vehicle from an own vehicle in a case where the obstacle vehicle is within a distance of a lane line according to an embodiment of the present invention.
Fig. 4 shows a schematic diagram for determining the degree of offset of an obstacle vehicle relative to an own vehicle in a case where the obstacle vehicle is outside the lane-line distance according to an embodiment of the present invention.
Fig. 5 shows a schematic diagram for determining the degree of offset of an obstacle vehicle relative to an own vehicle without road lane line information or with a very short lane line, according to an embodiment of the present invention.
Fig. 6 is a schematic block diagram showing a tracking target determining apparatus according to an embodiment of the present invention.
Detailed Description
The following describes embodiments of the present invention with reference to the drawings. These descriptions are exemplary and are intended to enable one skilled in the art to practice embodiments of the invention, and are not intended to limit the scope of the invention. Nothing in the description is described as being essential to the actual implementation but is irrelevant to the understanding of the invention.
Fig. 1 is a schematic flow chart illustrating a tracking target determining method according to an embodiment of the present invention. As shown in fig. 1, according to an embodiment of the present invention, a tracking target determination method according to the present invention first obtains obstacle vehicle information from a vehicle-mounted radar or a vehicle-mounted camera at step S100. The obstacle vehicle information can also be obtained by the arrangement and fusion of various sensors such as a vehicle-mounted radar and a vehicle-mounted camera. The obstacle vehicle information may include a lateral offset of the obstacle vehicle from the own vehicle in the present case, that isY obstacle Which represents the Y coordinate of the obstacle vehicle in the own vehicle coordinate system.
Then, in step S200, the own vehicle travel track is determined. According to one embodiment, the trajectory of the host vehicle can be determined from the lane center line in the presence of a lane line. It can be assumed that the center line of the travel locus of the own vehicle is always parallel to the center line of the lane line. In the case where there is no lane line, the center line of the own vehicle can be determined from the current position of the own vehicle and the angle of the steering wheel of the own vehicle.
Next, in step S300, an obstacle screening boundary is determined based on the own travel track. Fig. 2 illustrates an obstacle screening boundary determined in accordance with one embodiment of the present invention. In the embodiment of fig. 2, four sets of obstacle screening boundaries Bound1, bound3, bound4, and Bound2 are determined from the inside out, centered on the center line of the travel trajectory of the own vehicle (dashed line in the figure). The second obstacle screening boundary Bound3 is parallel to the first obstacle screening boundary Bound1, the third obstacle screening boundary Bound4 is wider at a position close to the host vehicle than at a position far from the host vehicle, and the fourth obstacle screening boundary Bound2 is narrower at a position close to the host vehicle than at a position far from the host vehicle. And all the obstacle screening boundaries are symmetrical with the center of the motion trail of the vehicle. The obstacle screening boundary can be adapted to the road situation, and obstacle vehicles to be tracked can be determined hierarchically.
The boundary condition of the obstacle screening is the coordinates of the points of the respective boundaries in the vehicle coordinate system. According to one embodiment, the coordinate values of each point are put into a table in advance, when a target is screened by using a boundary condition, the corresponding point is inquired from the table or an obstacle screening boundary is obtained by interpolation, and the boundary of the corresponding obstacle position can be used as much as possible according to the size and density of the table.
According to one embodiment, the width of the obstacle screening boundary closest to the center line of the driving track of the own vehicle is 0.2-0.4 lane width in the driving direction within a distance shorter than the speed of the own vehicle x the obstacle monitoring period x the near-end adjustment coefficient from the own vehicle; the width of the barrier screening boundary is 0.5-0.6 lane width in the distance range which is far away from the self vehicle, multiplied by the vehicle speed of the self vehicle, multiplied by the barrier monitoring period, multiplied by the far-end adjusting coefficient, and is 0.75-0.85 lane width in the distance range which is far away from the self vehicle, multiplied by the barrier monitoring period, multiplied by the near-end adjusting coefficient, but close to the distance range which is far away from the self vehicle, multiplied by the barrier monitoring period, multiplied by the far-end adjusting coefficient, wherein 1.5> far-end adjusting coefficient > near-end adjusting coefficient >1. According to the mode, the obstacle can be avoided relatively smoothly.
Next, returning to fig. 1, in step S400, the degree of deviation of the obstacle vehicle from the host vehicle is determined based on the obstacle vehicle information.
Fig. 3A and 3C are diagrams illustrating a determination of the degree of deviation of an obstacle vehicle from an own vehicle in a case where the obstacle vehicle is within a lane line information distance range according to an embodiment of the present invention. The lane line information distance is the farthest distance of the lane line that can be obtained by the sensor or the like.
As shown in fig. 3A to 3C, the broken line is the lane center line. According to one embodiment, the degree of offset of the obstacle vehicle relative to the own vehicle at the obstacle is determined according to the following formula:
Offset=Offset self +Offset obstacle
wherein, the first and the second end of the pipe are connected with each other,
Offset obstacle = Y obstacle— Offset lane
Y obstacle indicating the Y-coordinate of the obstacle vehicle in the own-vehicle coordinate system,Offset lane indicating the lateral offset of the lane centerline relative to the host vehicle at the obstacle vehicle,Offset self indicating the current lateral offset of the own vehicle relative to the lane centerline. Whether the obstacle vehicle is within the lane line may be given by road model fusion.Offset lane Also given by road model fusion. In the illustration in the figure, the position of the obstacle vehicle is its position point with its rear axle center coordinates. The own vehicle is a position point of which the rear axle center coordinates are. The road model being a combinationAnd obtaining a cubic spline curve by the lane line information given by the image.
The parameters in the formula have a certain positive-negative relation and are signed. When the obstacle is on the left side of the own vehicle,Y obstacle a positive value, a negative value when the own vehicle is on the right side; when the own vehicle is on the left side of the center line of the lane,Offset self andOffset lane negative values, and vice versa, positive values. When the obstacle is on the left side of the lane center line, calculatedOffset obstacle Should be positive, otherwise negative; finally calculatedOffsetA positive value indicates that the obstacle is on the left side of the own vehicle trajectory, whereas on the other hand, it is on the right side. Those skilled in the art will appreciate that the latter equations are similar. According to different situations, the parameter involved can be a positive value or a negative value.
In the case of the scene shown in fig. 3A (dark black in the figure indicates left and right lane lines, and the middle broken line indicates a lane center line), the host vehicle is located on the left side of the lane center line, and at this time, the host vehicle is located on the left side of the lane center lineOffset self Negative, assuming-1.2 m in this scenario, the obstacle is to the right of the host vehicle, whereY obstacle Negative, assuming-1.4 m in this scenario,Offset lane the distance of the lane center line from the longitudinal position of the obstacle is assumed to be-2.0 m in this scenario.
Then:Offset obstacle = Y obstacle — Offset lane =-1.4-(-2) = 0.6m
the obstacle is to the left of the lane center line,Offset obstacle positive values are 0.6m in this scenario.
Then theOffset=Offset self +Offset obstacle = -1.2+0.6=-0.6m
Negative values represent the obstacle to the right of the own vehicle trajectory at a lateral distance of 0.6m from the own vehicle trajectory.
Similarly, in the scenario of FIG. 3B, the host vehicle is to the left of the lane centerline, at which timeOffset self Negative values, assume-1.2 m in this scenario. The obstacle is arranged at the right side of the bicycle, whereinY obstacle Negative values, assume-2.7 m in this scenario.Offset lane Is the distance of the center line of the lane from the longitudinal position of the obstacle, which is-2.0 m in this scene.
Thus:
Offset obstacle = Y obstacle— Offset lane =-2.7-(-2) = -0.7m
the obstacle is to the right of the center line of the lane,Offset obstacle is negative, in this case-0.7 m
Offset=Offset self +Offset obstacle = -1.2+(-0.7) =-1.9m
Negative values represent a lateral distance of 1.9m from the own vehicle trajectory on the right side of the own vehicle trajectory.
Similarly, in the scenario of FIG. 3C, the host vehicle is to the left of the lane centerline, at which timeOffset self Negative values, assume-0.9 m in this scenario. The obstacle is positioned at the left side of the bicycle, whereinY obstacle Positive values assume 1.2m in this scenario.Offset lane Is the distance of the center line of the lane at the longitudinal position of the obstacle, which is assumed to be-2.0 m in this scenario.
Then there are:
Offset obstacle = Y obstacle— Offset lane =1.2-(-2) = 3.2m
the obstacle is to the left of the lane center line,Offset obstacle positive values are 3.2m in this scenario.
Offset=Offset self +Offset obstacle = -0.9+3.2=2.3m
Positive values represent a lateral distance of 2.3m from the own vehicle trajectory on the left side of the own vehicle trajectory.
The above description indicates that the above equations are all correct. The above numerical values are merely exemplary and do not limit the scope of the present invention.
Fig. 4 is a diagram illustrating a process of determining the degree of displacement of an obstacle vehicle from an own vehicle in a case where the obstacle vehicle is outside the lane line information distance range according to an embodiment of the present invention. In this case, the process can be performed by the following two steps a and B.
A. Extending the boundary of the lane line, wherein the extended boundary curve of the lane line meets the following conditions: the connecting point between the boundary of the lane line and the extension line of the boundary of the lane line is continuous, and the tangential direction of the extension line of the boundary of the lane line at the position of the obstacle vehicle is consistent with the orientation of the head of the obstacle vehicle, wherein the position of the obstacle vehicle refers to: the position of the obstacle vehicle in the own vehicle coordinate system corresponds to that in the figureX obstacle AndY obstacle 。
B. calculating the degree of offset of the obstacle vehicle with respect to the own vehicle according to the following formula
Offset=Offset self + Offset obstacle
Wherein the content of the first and second substances,
Offset obstacle = Y obstacle— Offset lane
Y obstacle indicating the Y-coordinate of the obstacle vehicle in the own-vehicle coordinate system,Offset lane indicating the lateral offset of the lane center line with respect to the own vehicle at the position of the obstacle vehicle,Offset self indicating the current lateral offset of the own vehicle relative to the lane center line. Can calculate the current lane where the own vehicle is positionedDetermining the current offset of the vehicle relative to the lane center line according to the width (image recognition, or information based on lane lines) and the current driving position of the vehicleOffset self 。
The above equations and their application can be referred to the description of fig. 3A to 3C.
Fig. 5 shows a schematic diagram for determining the degree of offset of an obstacle vehicle with respect to an own vehicle in the case where there is no lane line information or the lane line is shorter than a predetermined distance (hereinafter, the lane line is referred to as very short), according to an embodiment of the present invention. According to one embodiment, the predetermined distance is 10 meters. According to another embodiment, the predetermined distance is the vehicle speed x the obstacle monitoring period x 0.6, and according to such an embodiment, smooth handover between the lane line and the absence of the lane line can be achieved.
As shown in fig. 5, in the case where there is no road lane line information or the lane line is very short, the center line of the running track of the host vehicle is fitted first, and the lane width is taken as a predetermined value. According to one embodiment, a cubic curve is fitted to the self vehicle motion information and the heading angle (heading) of the obstacle vehicle as the center line of the lane line. According to one embodiment, the fitting method is to solve coefficients of a cubic spline according to the boundary condition, and the own vehicle motion information refers to a heading angle of the own vehicle, a curvature of a motion trajectory of the own vehicle, and a rate of change of curvature of the motion trajectory of the own vehicle (a curvature rate of change).
The fitted center line utilizes the curvature curve and the curvature change rate of the motion track of the vehicle, and simultaneously needs to meet the condition that the direction of the tangent line of the curve at the point A in the graph (the center line of the motion track of the vehicle is parallel to the obstacle vehicle, namely the vehicle catches up with the obstacle vehicle) is the same as the heading of the obstacle vehicle. It is assumed here that the obstacle vehicle is traveling parallel to the road centerline, so the cubic spline curve can be updated with the heading angle of the obstacle vehicle.
Then, the degree of offset of the obstacle vehicle with respect to the own vehicle can be calculated using the following formula
Offset=Y obstacle - Y lane
Offset = Offset×FilterConstant +Offset pre ×（1-FilterConstant）
Wherein, the value of the Filterconstant is determined according to the current curvature, the larger the current curvature is, the larger the value of the Filterconstant is, and 0<FilterConstant<1. Curvature is a physical quantity that describes the degree of curve curvature, with greater degrees of curvature being greater. The current curvature is the calculated curvature at that moment.Y lane Is the Y coordinate of the lane line at the obstacle in the own vehicle coordinate system.Y lane Itself also signed. When the own vehicle is on the left side of the fitted own vehicle running locus at the obstacle,Y lane is a negative value; when the fitted own vehicle running track at the obstacle is on the left side of the current own vehicle,Y lane positive values.
Returning to fig. 1, finally, in step S500, the obstacle vehicle to be tracked is determined based on the degree of deviation and the obstacle screening boundary. In this step, it may be first determined whether the obstacle vehicle is within the obstacle screening boundary based on the degree of deviation and the obstacle screening boundary. Then, when the obstacle vehicle reaches the first predetermined time t1 within the screening boundary, it is listed as an obstacle vehicle to be tracked.
According to one embodiment, the method further comprises determining whether the obstacle vehicle will change lanes according to the formula:
Offset=(Offset - Offset pre )/ Δt
by passingoffsetDetermines whether the obstacle vehicle will cut into and out of the lane.offsetIs the distance that the obstacle vehicle deviates from the center line of the road at the current moment,Offset pre refers to the distance of the obstacle vehicle from the center line of the roadway at the previous time. Δ t is the time difference between the two preceding and succeeding time instants.
And when the obstacle vehicle is determined to be cutting out the lane, performing obstacle vehicle de-tracking processing. The obstacle screening is performed by using a boundary, and the judgment of the obstacle vehicle cutting out the lane is judged by judging whether the change of the offset exceeds the screening boundary within the second preset time t 2. The conditions under which the obstacle vehicle is to be tracked should be more difficult than determining the obstacle vehicle that should be tracked. Specifically, for the obstacle vehicle cut-out, the obstacle vehicle goes beyond the screening boundary in a shorter time, i.e., the second predetermined time t2 is less than the first predetermined time t1.
According to one embodiment, the method of the invention further comprises the steps of:
(1) Judging whether the vehicle changes lanes or not; this step can be realized by judging the state of the turn light of the vehicle, the included angle between the vehicle and the lane line, etc.
(2) And adjusting the barrier screening boundary according to the preset amount towards the lane changing direction of the vehicle. The preset amount may be pre-stored. According to one embodiment, the preset amount may be determined by a table look-up method according to the current speed of the own vehicle. According to this method, custom customization can be achieved. Different users have different requirements on driving stability and the like, and barrier screening boundaries different from the current speed of the vehicle are set according to different user requirements, so that the requirements of the users can be better met.
The whole obstacle screening boundary is translated to the lane changing direction, so that the position of the obstacle screening boundary is changed from the position of the previous lane to the position of the new lane after the lane changing of the vehicle is completed.
(3) And adjusting the offset degree of the obstacle vehicle relative to the self vehicle according to the following formula in the lane changing direction of the self vehicle:
Offset = Offset-width/2
wherein, width represents the width of the obstacle.
Fig. 6 is a schematic block diagram showing a tracking target determining apparatus according to an embodiment of the present invention. As shown in fig. 6, according to an embodiment of the present invention, the tracking target determining apparatus 10 includes: an obstacle vehicle information obtaining unit 100 that obtains obstacle vehicle information by a vehicle-mounted radar or a vehicle-mounted camera; a self-vehicle travel track determination unit 200 for determining a self-vehicle travel track; an obstacle screening boundary determination unit 300 for determining an obstacle screening boundary based on a running track of the own vehicle; an obstacle vehicle offset degree determination unit 400 configured to determine an offset degree of the obstacle vehicle with respect to the own vehicle, based on the obstacle vehicle information; and a tracked vehicle determination unit 500 for determining an obstacle vehicle to be tracked according to the deviation degree and the obstacle screening boundary.
According to one embodiment, the obstacle screening boundary determination unit 300 determines, for an obstacle screening boundary closest to a center line of the own vehicle, a width of the obstacle screening boundary to be 0.2 to 0.4 lane width in a traveling direction within a distance shorter than a vehicle speed of the own vehicle x an obstacle monitoring period x a near-end adjustment coefficient from the own vehicle; the width of the obstacle screening boundary is 0.5-0.6 lane width in a distance range which is far away from the self vehicle, multiplied by the self vehicle speed, multiplied by the obstacle monitoring period, multiplied by the far-end adjusting coefficient, and is 0.75-0.85 lane width in a distance range which is far away from the self vehicle, multiplied by the self vehicle speed, multiplied by the obstacle monitoring period, multiplied by the near-end adjusting coefficient, but close to the self vehicle, multiplied by the self vehicle speed, multiplied by the obstacle monitoring period, multiplied by the far-end adjusting coefficient, wherein 1.5> far-end adjusting coefficient > near-end adjusting coefficient >1.
According to one embodiment, the obstacle screening boundary determination unit 300 determines a plurality of obstacle screening boundaries, a second obstacle screening boundary being parallel to a first obstacle screening boundary, a third obstacle screening boundary being wider at a position close to the own vehicle than at a position away from the own vehicle, and a fourth obstacle screening boundary being narrower at a position close to the own vehicle than at a position away from the own vehicle in the vehicle traveling direction, the obstacle screening boundaries being symmetrical about the center of the movement locus of the own vehicle.
According to one embodiment, the obstacle vehicle offset degree determination unit 400 determines the offset degree of the obstacle vehicle from the own vehicle as follows:
(1) When the obstacle vehicle is within the lane line information distance range, the degree of deviation of the obstacle vehicle from the host vehicle is calculated according to the following formula
Offset=Offset self +Offset obstacle
Wherein the content of the first and second substances,
Offset obstacle = Y obstacle— Offset lane
Y obstacle a Y coordinate indicating the obstacle vehicle in the coordinate system of the own vehicle,Offset lane indicating the lateral offset of the lane centerline relative to the host vehicle at the obstacle vehicle,Offset self represents the lateral offset of the own vehicle relative to the center line of the lane at present;
(2) When the obstacle vehicle is outside the lane line information distance range,
(2.1) extending the boundary of the lane line, wherein the extended curve meets the conditions: the connecting points of the boundary extension lines of the lane lines and the boundary extension lines of the lane lines are continuous, and the tangential direction of the boundary extension lines of the lane lines at the position of the obstacle vehicle is consistent with the direction of the head of the obstacle vehicle;
(2.2) calculating the degree of offset of the obstacle vehicle from the own vehicle according to the following formula
Offset=Offset self +Offset obstacle
Wherein the content of the first and second substances,
Offset obstacle = Y obstacle— Offset lane
Y obstacle indicating the Y-coordinate of the obstacle vehicle in the own-vehicle coordinate system,Offset lane indicating the lateral offset of the lane centerline relative to the host vehicle at the obstacle vehicle,Offset self indicating the current lateral offset of the own vehicle relative to the center line of the lane,
(3) In the case where there is no road lane line information or the lane line is shorter than a predetermined distance, the degree of deviation of the obstacle vehicle from the own vehicle is determined as follows:
(3.1) fitting and estimating the central line of the lane line, and taking the width of the lane as a preset value;
(3.2) calculating the degree of offset of the obstacle vehicle with respect to the own vehicle using the following formula
Offset=Y obstacle - Y lane
Offset = Offset×FilterConstant +Offset pre ×（1-FilterConstant）
The value of the Filterconstant is determined according to the curvature of the currently fitted lane line track, and the larger the curvature is, the larger the value of the Filterconstant is, and 0<FilterConstant<1。Y lane Is the Y-coordinate of the lane line at the obstacle in the own vehicle coordinate system, wherein, when the obstacle is on the left side of the own vehicle,Y obstacle and is positive, at the right side of the own vehicle,Y obstacle is a negative value; when the own vehicle is on the left side of the center line of the lane,Offset self andOffset lane and is negative, when the own vehicle is on the right side of the center line of the lane,Offset self andOffset lane is a positive value; when the own vehicle is on the left side of the fitted own vehicle running locus at the obstacle,Y lane is a negative value; when the fitted own vehicle running track at the obstacle is on the left side of the current own vehicle,Y lane positive values.
According to one embodiment, the fitted center line utilizes the curvature and the curvature change rate of the own vehicle motion trajectory and at the same time needs to satisfy that at the parallel position with the obstacle vehicle, the direction of the tangent of the curve is the same as the heading of the obstacle vehicle.
According to one embodiment, the apparatus further includes an obstacle vehicle lane change determination unit (not shown in the drawings) that determines whether the obstacle vehicle will change lanes according to the following formula:
Offset’=( Offset - Offset pre )/ Δt
offsetis the distance of the target vehicle deviating from the center line of the road at the current moment,Offset pre refers to the distance of the obstacle vehicle from the center line of the roadway at the previous time. Δ t is the time difference between two successive times, when based onoffsetChange of (2)offset’And when the self vehicle is judged to exceed the screening boundary within the second preset time t2 in advance, judging that the obstacle vehicle will cut out the lane.
According to one embodiment, the device further comprises a lane change processing unit of the own vehicle, which processes the lane change processing unit
(1) Judging whether the vehicle changes lanes or not;
(2) And adjusting the offset degree of the obstacle vehicle relative to the self vehicle according to the following formula in the lane changing direction of the self vehicle:
Offset = Offset-width/2
wherein, width represents the width of the obstacle.
(3) And adjusting the barrier screening boundary according to the preset amount towards the lane changing direction of the vehicle.
Those skilled in the art will readily appreciate that the above description of the method may be utilized to understand the apparatus of the present invention.
Those skilled in the art will readily appreciate that the method of the present invention may also include other steps corresponding to the functions performed by the apparatus of the present invention. The steps above may also be reduced.
The numbering of elements and steps of the present invention is merely for convenience of description and does not imply an order of execution unless the context dictates otherwise.
Those skilled in the art will appreciate that the above units can be implemented by software or special hardware, such as a field programmable gate array, a single chip, or a microchip, or by a combination of software and hardware.
The present invention also provides an electronic device, comprising: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the method of the present invention.
The invention also relates to a computer software which, when executed by a computing device (such as a single chip, a computer, a CPU, etc.), can implement the method of the invention.
The present invention also relates to a computer software storage device, such as a hard disk, a floppy disk, a flash memory, etc., which stores the above computer software.
The description of the method or steps of the invention may be used for understanding the description of the unit or device, and the description of the unit or device may be used for understanding the method or steps of the invention.
The vehicle-mounted radar or the vehicle-mounted camera of the invention is to be widely understood and is a technology which is known now or in the future and can obtain the information of the obstacle.
The above description is intended to be illustrative, and not restrictive, and any changes and substitutions that come within the spirit of the invention are desired to be protected.

Claims (9)

1. A tracking target determination method is characterized by comprising the following steps:
obtaining obstacle vehicle information by a vehicle-mounted radar or a vehicle-mounted camera;
determining the running track of the vehicle;
determining an obstacle screening boundary based on the driving track of the vehicle;
determining the offset degree of the obstacle vehicle relative to the vehicle according to the obstacle vehicle information;
determining the obstacle vehicle to be tracked according to the deviation degree and the obstacle screening boundary,
wherein the degree of offset of the obstacle vehicle relative to the own vehicle is determined as follows:
(1) When the obstacle vehicle is within the lane line information distance range, the degree of deviation of the obstacle vehicle from the host vehicle is calculated according to the following formula
Offset=Offset self +Offset obstacle
Wherein, the first and the second end of the pipe are connected with each other,
Offset obstacle = Y obstacle— Offset lane
Y obstacle a Y coordinate indicating the obstacle vehicle in the coordinate system of the own vehicle,Offset lane indicating the lateral offset of the lane centerline relative to the host vehicle at the obstacle vehicle,Offset self represents the lateral offset of the own vehicle relative to the center line of the lane at present;
(2) When the obstacle vehicle is outside the lane line information distance range,
(2.1) extending the boundary of the lane line, wherein the extended curve meets the conditions: the connection points of the boundary extension lines of the lane lines and the boundary extension lines of the lane lines are continuous, and the direction of the tangent line of the boundary extension lines of the lane lines at the position of the obstacle vehicle is consistent with the direction of the head of the obstacle vehicle;
(2.2) calculating the degree of offset of the obstacle vehicle with respect to the own vehicle according to the following formula
Offset=Offset self +Offset obstacle
Wherein the content of the first and second substances,
Offset obstacle = Y obstacle— Offset lane
Y obstacle indicating the Y-coordinate of the obstacle vehicle in the own-vehicle coordinate system,Offset lane indicating the lateral offset of the lane centerline relative to the host vehicle at the obstacle vehicle,Offset self indicating that the own vehicle is currently laterally offset with respect to the lane center line,
(3) In the case where there is no road lane line information or the lane line is shorter than a predetermined distance, the degree of deviation of the obstacle vehicle from the own vehicle is determined as follows:
(3.1) fitting and estimating the central line of the lane line, and taking the lane width as a preset value;
(3.2) calculating the degree of offset of the obstacle vehicle with respect to the own vehicle using the following formula
Offset=Y obstacle - Y lane
Offset = Offset×FilterConstant +Offset pre ×（1-FilterConstant）
Wherein, the value of the Filterconstant is determined according to the curvature of the lane line track which is fitted currently, the larger the curvature is, the larger the value of the Filterconstant is, and 0<FilterConstant<1，Y lane Is the Y-coordinate of the lane line at the obstacle in the own vehicle coordinate system,
wherein, when the obstacle is on the left side of the own vehicle,Y obstacle and is positive, on the right side of the own vehicle,Y obstacle is a negative value; when the own vehicle is on the left side of the center line of the lane,Offset self andOffset lane and is negative, when the own vehicle is on the right side of the center line of the lane,Offset self andOffset lane is a positive value; when the own vehicle is on the left side of the fitted own vehicle running track at the obstacle,Y lane is a negative value; when the fitted own vehicle running track at the obstacle is on the left side of the current own vehicle,Y lane a positive value.
2. The tracking target determination method according to claim 1, wherein a width of the obstacle screening boundary is 0.2 to 0.4 lane width in a distance in a traveling direction from the own vehicle shorter than a speed of the own vehicle x an obstacle monitoring period x a near-end adjustment coefficient with respect to the obstacle screening boundary closest to a center line of the own vehicle; the width of the barrier screening boundary is 0.5-0.6 lane width in the distance range which is far away from the self vehicle, multiplied by the self vehicle speed, multiplied by the barrier monitoring period and multiplied by the far-end adjusting coefficient, and the width of the barrier screening boundary is 0.75-0.85 lane width in the distance range which is far away from the self vehicle, multiplied by the self vehicle speed, multiplied by the barrier monitoring period, multiplied by the near-end adjusting coefficient, but close to the self vehicle, multiplied by the self vehicle speed, multiplied by the barrier monitoring period, multiplied by the far-end adjusting coefficient, wherein 1.5> far-end adjusting coefficient > near-end adjusting coefficient >1.
3. The tracking target determination method according to claim 1, characterized in that a plurality of obstacle screening boundaries are determined, a second obstacle screening boundary of which is parallel to the first obstacle screening boundary, a third obstacle screening boundary being a shape that is wider at a position close to the own vehicle than at a position far from the own vehicle, and a fourth obstacle screening boundary being a shape that is narrower at a position close to the own vehicle than at a position far from the own vehicle in the vehicle traveling direction, the obstacle screening boundaries being symmetrical about the center of the movement locus of the own vehicle.
4. The tracking target determining method according to claim 1, wherein the center line of the fitted estimated lane line uses the curvature of the motion trajectory of the own vehicle and the curvature change rate, and simultaneously needs to satisfy that the direction of the tangent of the curve is the same as the heading of the obstacle vehicle at a position parallel to the obstacle vehicle, wherein the predetermined distance is the vehicle speed of the own vehicle x the obstacle monitoring period x 0.6.
5. The tracking target determination method according to claim 1, further comprising determining whether the obstacle vehicle will change lanes according to the following formula:
Offset’=( Offset - Offset pre )/ Δt
offsetis the distance that the obstacle vehicle deviates from the center line of the road at the current moment,Offset pre refers to the distance of the obstacle vehicle from the center line of the road at the previous moment, deltat is the time difference between the previous moment and the next moment,
when according tooffsetVariations of (2)offset’And when the obstacle vehicle is predicted to exceed the screening boundary within the second preset time t2, judging that the obstacle vehicle will cut out the lane.
6. The tracking target determination method according to claim 1, characterized in that the method further comprises:
(1) Judging whether the vehicle changes lanes or not;
(2) And adjusting the offset degree of the obstacle vehicle relative to the self vehicle according to the following formula in the lane changing direction of the self vehicle:
Offset = Offset-width/2
wherein, width represents the width of the barrier,
(3) And adjusting the barrier screening boundary according to the preset amount towards the lane changing direction of the vehicle.
7. A tracking target determination apparatus, characterized by comprising:
an obstacle vehicle information obtaining unit that obtains obstacle vehicle information by a vehicle-mounted radar or a vehicle-mounted camera;
a self vehicle running track determining unit for determining a self vehicle running track;
an obstacle screening boundary determination unit for determining an obstacle screening boundary based on a running track of the own vehicle;
the obstacle vehicle offset degree determining unit is used for determining the offset degree of the obstacle vehicle relative to the vehicle according to the obstacle vehicle information;
a tracked vehicle determining unit for determining an obstacle vehicle to be tracked according to the deviation degree and the obstacle screening boundary,
wherein the obstacle vehicle offset degree determination unit determines the offset degree of the obstacle vehicle with respect to the own vehicle as follows:
(1) When the obstacle vehicle is within the lane line information distance range, the degree of deviation of the obstacle vehicle from the host vehicle is calculated according to the following formula
Offset=Offset self +Offset obstacle
Wherein the content of the first and second substances,
Offset obstacle = Y obstacle— Offset lane
Y obstacle a Y coordinate indicating the obstacle vehicle in the coordinate system of the own vehicle,Offset lane indicating the lateral offset of the lane centerline relative to the host vehicle at the obstacle vehicle,Offset self represents the lateral offset of the own vehicle relative to the center line of the lane at present;
(2) When the obstacle vehicle is outside the lane line information distance range,
(2.1) extending the boundary of the lane line, wherein the extended curve meets the condition: the connection points of the boundary extension lines of the lane lines and the boundary extension lines of the lane lines are continuous, and the direction of the tangent line of the boundary extension lines of the lane lines at the position of the obstacle vehicle is consistent with the direction of the head of the obstacle vehicle;
(2.2) calculating the degree of offset of the obstacle vehicle from the own vehicle according to the following formula
Offset=Offset self +Offset obstacle
Wherein, the first and the second end of the pipe are connected with each other,
Offset obstacle = Y obstacle— Offset lane
Y obstacle indicating the Y-coordinate of the obstacle vehicle in the own-vehicle coordinate system,Offset lane indicating the lateral offset of the lane centerline relative to the host vehicle at the obstacle vehicle,Offset self indicating that the own vehicle is currently laterally offset with respect to the lane center line,
(3) In the case where there is no road lane line information or the lane line is shorter than a predetermined distance, the degree of deviation of the obstacle vehicle from the own vehicle is determined as follows:
(3.1) fitting and estimating the central line of the lane line, and taking the lane width as a preset value;
(3.2) calculating the degree of offset of the obstacle vehicle with respect to the own vehicle using the following formula
Offset=Y obstacle - Y lane
Offset = Offset×FilterConstant +Offset pre ×（1-FilterConstant）
Wherein, the value of the Filterconstant is determined according to the curvature of the lane line track which is fitted currently, the larger the curvature is, the larger the value of the Filterconstant is, and 0<FilterConstant<1，Y lane Is the Y-coordinate of the lane line at the obstacle in the own vehicle coordinate system,
wherein, when the obstacle is on the left side of the own vehicle,Y obstacle and is positive, at the right side of the own vehicle,Y obstacle is a negative value; when the own vehicle is on the left side of the center line of the lane,Offset self andOffset lane and is negative, when the own vehicle is on the right side of the center line of the lane,Offset self andOffset lane is a positive value; when the own vehicle is on the left side of the fitted own vehicle running locus at the obstacle,Y lane is a negative value; when the fitted own vehicle running track at the obstacle is on the left side of the current own vehicle,Y lane positive values.
8. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the method of any one of claims 1 to 6.
9. A computer-readable storage medium, on which a device control program is stored, which, when executed by a processor, implements the method of any one of claims 1 to 6.
CN202210548956.XA 2022-05-20 2022-05-20 Tracking target determination method and device, electronic equipment and storage medium Active CN114643988B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210548956.XA CN114643988B (en) 2022-05-20 2022-05-20 Tracking target determination method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210548956.XA CN114643988B (en) 2022-05-20 2022-05-20 Tracking target determination method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN114643988A CN114643988A (en) 2022-06-21
CN114643988B true CN114643988B (en) 2022-10-21

Family

ID=81997853

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210548956.XA Active CN114643988B (en) 2022-05-20 2022-05-20 Tracking target determination method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114643988B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115661797B (en) * 2022-12-06 2023-05-09 清华大学 Target tracking method, device and equipment

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104527644A (en) * 2014-12-29 2015-04-22 江苏大学 Self-adaption cruise system and method
CN110758392A (en) * 2019-10-17 2020-02-07 中通客车控股股份有限公司 Autonomous lane change control method for passenger car
CN111731289A (en) * 2020-06-24 2020-10-02 中国第一汽车股份有限公司 Following control method and device, vehicle and storage medium
CN112009473A (en) * 2020-10-16 2020-12-01 福瑞泰克智能系统有限公司 Method and device for selecting self-adaptive cruise target and computer equipment
CN112572472A (en) * 2020-12-08 2021-03-30 重庆大学 Automatic driving collision prediction method based on Frenet coordinate system
CN112644489A (en) * 2019-10-11 2021-04-13 现代自动车株式会社 Lane following control apparatus and method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20210062143A (en) * 2019-11-20 2021-05-31 현대자동차주식회사 Apparatus for displaying steering information of preceding vehicle and method thereof
CN114655208A (en) * 2020-12-04 2022-06-24 上海汽车集团股份有限公司 Method and device for determining obstacle vehicle behind vehicle

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104527644A (en) * 2014-12-29 2015-04-22 江苏大学 Self-adaption cruise system and method
CN112644489A (en) * 2019-10-11 2021-04-13 现代自动车株式会社 Lane following control apparatus and method
CN110758392A (en) * 2019-10-17 2020-02-07 中通客车控股股份有限公司 Autonomous lane change control method for passenger car
CN111731289A (en) * 2020-06-24 2020-10-02 中国第一汽车股份有限公司 Following control method and device, vehicle and storage medium
CN112009473A (en) * 2020-10-16 2020-12-01 福瑞泰克智能系统有限公司 Method and device for selecting self-adaptive cruise target and computer equipment
CN112572472A (en) * 2020-12-08 2021-03-30 重庆大学 Automatic driving collision prediction method based on Frenet coordinate system

Also Published As

Publication number Publication date
CN114643988A (en) 2022-06-21

Similar Documents

Publication Publication Date Title
WO2021259000A1 (en) Method and apparatus for controlling vehicle following, vehicle, and storage medium
US10776634B2 (en) Method for determining the course of the road for a motor vehicle
US9045144B2 (en) Third-order polynomial-based course prediction for driver assistance functions
US9592829B2 (en) Method and control unit for robustly detecting a lane change of a vehicle
CN107128366A (en) System and method for following path to the track that towing vehicle provides correction by bend
CN107209998B (en) Lane line recognition device and lane line recognition method
JP3608259B2 (en) Automobile route estimation device
JP7193656B2 (en) Control unit and method for recognizing intruding or exiting vehicles
CN115087573B (en) Key target selection method, device and system
CN114643988B (en) Tracking target determination method and device, electronic equipment and storage medium
JP7149121B2 (en) VEHICLE CONTROL DEVICE, VEHICLE CONTROL METHOD AND VEHICLE CONTROL SYSTEM
WO2022095023A1 (en) Traffic stream information determination method and apparatus, electronic device and storage medium
WO2023050811A1 (en) Driving device control method, apparatus, electronic device, storage medium, and computer program product
JP5359289B2 (en) Vehicle driving support device
CN113511221B (en) Method, system, vehicle and storage medium for monitoring transverse control capability
CN114518119A (en) Positioning method and device
CN111688683B (en) Vehicle driving state control method, device, computer equipment and storage medium
US11987251B2 (en) Adaptive rationalizer for vehicle perception systems toward robust automated driving control
CN114347994B (en) Lane line position estimation method and apparatus, electronic device, and storage medium
JP4615954B2 (en) Vehicle control object determination device
KR102427366B1 (en) Lane estimation method and apparatus using deep neural network
CN115303288A (en) Vehicle control method, control device and camera device
US11913794B2 (en) Determining a vehicle trajectory utilizing boundary cost functions
JP4046742B2 (en) Road shape estimation device
CN114817765A (en) Map-based target course disambiguation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant