CN110696823A - Method and system for predicting collision time of vehicle and vehicle - Google Patents

Method and system for predicting collision time of vehicle and vehicle Download PDF

Info

Publication number
CN110696823A
CN110696823A CN201910978601.2A CN201910978601A CN110696823A CN 110696823 A CN110696823 A CN 110696823A CN 201910978601 A CN201910978601 A CN 201910978601A CN 110696823 A CN110696823 A CN 110696823A
Authority
CN
China
Prior art keywords
vehicle
target obstacle
target
self
time
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.)
Granted
Application number
CN201910978601.2A
Other languages
Chinese (zh)
Other versions
CN110696823B (en
Inventor
张子期
邓堃
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.)
Zhejiang Geely Holding Group Co Ltd
Zhejiang Geely Automobile Research Institute Co Ltd
Original Assignee
Zhejiang Geely Holding Group Co Ltd
Zhejiang Geely Automobile Research Institute 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 Zhejiang Geely Holding Group Co Ltd, Zhejiang Geely Automobile Research Institute Co Ltd filed Critical Zhejiang Geely Holding Group Co Ltd
Priority to CN201910978601.2A priority Critical patent/CN110696823B/en
Publication of CN110696823A publication Critical patent/CN110696823A/en
Application granted granted Critical
Publication of CN110696823B publication Critical patent/CN110696823B/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
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a method and a system for predicting collision time of a vehicle and the vehicle, and relates to the field of vehicles. The method comprises the steps of firstly obtaining the type of a target obstacle, the observation angle and distance of the target obstacle and the coordinates of four vertex angles of a self vehicle, then determining the expansion radius of the target obstacle according to the type of the target obstacle, then calculating new coordinates of the four vertex angles of the self vehicle according to the coordinates and the expansion radius of the four vertex angles of the self vehicle, then converting the observation angle of the target obstacle relative to a detection module into the observation angle of the new coordinates of the four vertex angles according to the new coordinates of the four vertex angles of the self vehicle, then calculating initial predicted collision time according to the observation angle of the new coordinates of the four vertex angles of the self vehicle, and finally calculating the final predicted collision time when the target obstacle collides with the self vehicle according to the initial predicted collision time. The invention can calculate the predicted collision time only by depending on the type, observation angle and distance of the target obstacle, and has low dependence on the target obstacle.

Description

Method and system for predicting collision time of vehicle and vehicle
Technical Field
The invention relates to the field of vehicles, in particular to a method and a system for predicting collision time of a vehicle and the vehicle.
Background
Automatic Emergency Braking (AEB) is a passive safety technology, and when a collision risk in front of a vehicle is detected, a warning is given to remind a driver, and if the driver does not react correctly, the system avoids collision or reduces the collision degree through automatic Braking. At present, the technology is mainly applied to Advanced Driver Assistance Systems (ADAS), and possible accidents caused by automatic Driving function defects can be remedied by applying AEB in the process of transition of an automatic Driving level from L2 to L5 in the field of Automatic Driving (AD).
However, in the prior art, the detection of the collision target is mainly directed to the front side collision target in the rear-end collision scene, and the detection algorithms of the collision target related to the traffic intersection scene, for example, the left-turn collision scene, are fewer. In the prior art, most algorithms can be calculated only by relying on much information, the dependence is strong, and the application scene is very limited.
Disclosure of Invention
The invention aims to provide a method for predicting the time of collision of a vehicle, which solves the problem that in the prior art, an algorithm for detecting the collision needs to rely on a lot of information to calculate so that the dependency is strong.
A further object of the first aspect of the present invention is to improve the safety of the vehicle and expand the applicable fields.
It is an object of a second aspect of the present invention to provide a system for estimating a time to collision of a vehicle.
It is an object of a third aspect of the invention to provide a vehicle.
According to a first aspect of the present invention, there is provided a method of predicting a time to collision of a vehicle, comprising:
acquiring target obstacle information and coordinates of four vertex angles of a self vehicle, wherein the target obstacle information comprises the type of a target obstacle and the observation angle and distance of the target obstacle relative to a detection module arranged on the self vehicle;
determining the expansion radius of the target obstacle according to the type of the target obstacle, wherein a plurality of circles with the same size are used for enveloping the target obstacle, the center of each circle is located on the longitudinal central axis of the target obstacle, and the minimum radius of each circle is taken as the expansion radius;
calculating new coordinates of the four vertex angles of the self-vehicle after expansion treatment according to the coordinates of the four vertex angles of the self-vehicle and the expansion radius;
converting the observation angle of the target obstacle relative to the detection module into an observation angle of a new coordinate relative to the four top corners of the vehicle according to the new coordinate of the four top corners of the vehicle;
calculating initial expected collision time according to the observation angles of the new coordinates of the four top angles of the self-vehicle;
and judging whether the target barrier collides with the self vehicle or not according to the initial predicted collision time, and if so, calculating to obtain the final predicted collision time.
Optionally, determining an expansion radius of the target obstacle according to the type of the target obstacle specifically includes:
searching size information of the target obstacle corresponding to the type of the target obstacle from a preset storage module according to the type of the target obstacle, wherein the preset storage module stores the corresponding relation between the type of the target obstacle and the size information in advance, and the type of the target obstacle is a vehicle or a person;
calculating the expansion radius of the target obstacle according to the type of the target obstacle and the size information, wherein a specific calculation formula is as follows:
Figure BDA0002234453580000021
wherein R is an expansion radius, W is a width of the target obstacle, L is a length of the target obstacle, and N is the number of circles determined according to the type of the target obstacle.
Optionally, the observation angle of the target obstacle relative to the detection module is converted into the observation angle of the new coordinate relative to the four top corners of the host vehicle according to the new coordinate of the four top corners of the host vehicle, and a specific conversion formula is as follows:
Figure BDA0002234453580000022
Xi＝dicosθi
Yi＝disinθi；
wherein d isiIs the distance theta of the target obstacle relative to the detection moduleiIs the observation angle, X, of the target obstacle relative to the detection moduleiIs the abscissa, Y, of the target obstacle relative to the detection moduleiIs the ordinate, X, of the target obstacle relative to the detection module*The abscissa and Y are new coordinates of four vertex angles of the bicycle*Is the ordinate theta of the new coordinate of the four apex angles of the bicycle*And the observation angle of the target obstacle relative to the new coordinates of the four top corners of the self-vehicle is obtained.
Optionally, after converting the observation angle of the target obstacle relative to the detection module into an observation angle relative to new coordinates of four top corners of the host vehicle according to the new coordinates of the four top corners of the host vehicle, the method further includes:
and acquiring a plurality of observation angles of the target obstacle corresponding to new coordinates of four vertex angles of the self vehicle at a plurality of moments within a preset time range.
Optionally, the initial predicted collision time is calculated according to the observation angles of the new coordinates of the four top corners of the host vehicle, and a specific calculation formula is as follows:
Figure BDA0002234453580000031
wherein, t0For the current time, t is a time in the future,
Figure BDA0002234453580000032
achieving observation angles for fitting new coordinates of the target obstacle relative to four top angles of the self-vehiclePresetting the shortest time of a time threshold;
Ploy*(t) is a polynomial used to fit the observation angle, the polynomial being as follows:
Figure BDA0002234453580000033
a is obtained by calculating a plurality of observation angles of the target obstacle corresponding to the new coordinates of the four top angles of the self vehicle at a plurality of moments in the preset time range3，a2，a1，a0；
Get PLF，PRF，PLR，PRRRespectively showing observation from a left front top corner, a right front top corner, a left rear top corner and a right rear top corner of the bicycle;
θΔfour characteristic observation angles of 90 degrees, -90 degrees, 0 degrees and 180 degrees are taken, the clockwise direction is negative, and the anticlockwise direction is positive.
Optionally, the initial predicted collision time is calculated according to the observation angles of the new coordinates of the four top corners of the host vehicle, and the specific calculation formula may also be:
Figure BDA0002234453580000034
wherein, deltaΔThe value range is [ -30 DEG, 30 DEG ]]。
Optionally, it is determined whether the target obstacle collides with the host vehicle according to the initial predicted collision time, and if so, a final predicted collision time is calculated, which specifically includes:
according to
Figure BDA0002234453580000035
Judging whether the target barrier collides with the front side of the bicycle or not, and if so, judging whether the target barrier collides with the front side of the bicycle
Figure BDA0002234453580000036
Andwhen the absolute value of the difference is less than a preset time threshold value, the target obstacle is judged to collide with the front side of the vehicle, and the time for predicting the collision with the front side of the vehicle is
Figure BDA0002234453580000038
And
Figure BDA0002234453580000039
minimum value therebetween, i.e.
Figure BDA0002234453580000041
According to
Figure BDA0002234453580000042
Judging whether the target barrier collides with the left side of the self-vehicle or not, and judging whether the target barrier collides with the left side of the self-vehicle or not when the target barrier collides with the left side of the self-vehicleAnd
Figure BDA0002234453580000044
when the absolute value of the difference is smaller than the preset time threshold value, the target barrier is judged to collide with the left side of the self-vehicle, and the predicted time for colliding with the left side of the self-vehicle is
Figure BDA0002234453580000045
And
Figure BDA0002234453580000046
minimum value therebetween, i.e.
Figure BDA0002234453580000047
The final expected time to collision is
Figure BDA0002234453580000048
And
Figure BDA0002234453580000049
minimum betweenValue, i.e.
Figure BDA00022344535800000410
Optionally, whether the target obstacle collides with the own vehicle is judged according to the initial predicted collision time, if yes, a final predicted collision time is calculated, and the method specifically includes:
according to
Figure BDA00022344535800000411
Judging whether the target barrier collides with the right side of the vehicle or not, and judging whether the target barrier collides with the right side of the vehicle or not
Figure BDA00022344535800000412
And
Figure BDA00022344535800000413
when the absolute value of the difference is smaller than the preset time threshold value, the target barrier is judged to collide with the right side of the self-vehicle, and the predicted time for colliding with the right side of the self-vehicle isAnd
Figure BDA00022344535800000415
minimum value therebetween, i.e.
Figure BDA00022344535800000416
According to
Figure BDA00022344535800000417
Judging whether the target barrier collides with the tail side of the vehicle or not, and if so, judging whether the target barrier collides with the tail side of the vehicle
Figure BDA00022344535800000418
And
Figure BDA00022344535800000419
when the absolute value of the difference is smaller than the preset time threshold value, the target obstacle is judged to be sent from the tail side of the vehicleIn case of collision, the time of collision with the rear side of the vehicle is estimated to be
Figure BDA00022344535800000420
And
Figure BDA00022344535800000421
minimum value therebetween, i.e.
Figure BDA00022344535800000422
The final expected time to collision is
Figure BDA00022344535800000423
Minimum value therebetween, i.e.
Figure BDA00022344535800000424
According to the object of the second aspect of the present invention, the present invention also provides a system applied to the method for estimating the time of collision of the vehicle, comprising a detection module and a calculation module,
the detection module is arranged on the self-vehicle and used for acquiring the information of the target obstacle and coordinates of four top corners of the self-vehicle, and the detection module is also used for acquiring a plurality of observation angles of the target obstacle corresponding to new coordinates of the four top corners of the self-vehicle at a plurality of moments within a preset time range;
and the calculation module is used for calculating the final predicted collision time according to the received target obstacle information, the coordinates of the four top corners of the vehicle and a plurality of observation angles of the target obstacle corresponding to the new coordinates of the four top corners of the vehicle at a plurality of moments.
According to the object of the second aspect of the invention, the invention also provides a vehicle equipped with the system as described above.
The method comprises the steps of firstly obtaining the type of a target obstacle, the observation angle and the distance of the target obstacle relative to a detection module arranged on a self-vehicle and the coordinates of four vertex angles of the self-vehicle, then determining the expansion radius of the target obstacle according to the type of the target obstacle, secondly calculating new coordinates of the four vertex angles of the self-vehicle after expansion processing according to the coordinates and the expansion radius of the four vertex angles of the self-vehicle, thirdly converting the observation angle of the target obstacle relative to the detection module into the observation angle of the new coordinates of the four vertex angles of the self-vehicle according to the new coordinates of the four vertex angles of the self-vehicle, thirdly calculating initial predicted collision time according to the observation angles of the new coordinates of the four vertex angles of the self-vehicle, and finally calculating the final predicted collision time when the target obstacle collides with the self-vehicle according to the initial predicted. The invention can calculate the predicted collision time only by depending on the type of the target obstacle and the observation angle and the distance of the target obstacle relative to the detection module arranged on the self-vehicle, and has low dependence degree on the target obstacle and strong robustness.
Furthermore, the method can respectively calculate the estimated time of collision between the target barrier and the periphery of the self-vehicle through detection, and improves the safety of the vehicle compared with the possibility that the collision between the front target barrier and the self-vehicle can only be detected in the prior art, and has wide application scenes.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Some specific embodiments of the invention will be described in detail hereinafter, by way of illustration and not limitation, with reference to the accompanying drawings. The same reference numbers in the drawings identify the same or similar elements or components. Those skilled in the art will appreciate that the drawings are not necessarily drawn to scale. In the drawings:
FIG. 1 is a schematic flow chart diagram of a method of estimating a time to collision of a vehicle in accordance with one embodiment of the present invention;
FIG. 2 is a schematic representation of an observation angle of a target obstacle relative to a detection module in accordance with one embodiment of the present invention;
FIG. 3 is a schematic relationship diagram of the type of target obstruction versus expansion radius in accordance with one embodiment of the present invention;
FIG. 4 is a schematic relationship diagram of new coordinates and original coordinates of four corners of a bicycle after expansion processing according to one embodiment of the invention;
FIG. 5 is a schematic representation of a target obstacle colliding with a front side of a host vehicle in accordance with one embodiment of the present invention;
FIG. 6 is a schematic representation of a target obstacle colliding with the left side of a host vehicle in accordance with another embodiment of the present invention;
FIG. 7 is a schematic representation of a target obstacle colliding with the right side of the host vehicle in accordance with yet another embodiment of the present invention;
FIG. 8 is a schematic representation of a target obstacle colliding with a rear side of a vehicle according to yet another embodiment of the present invention;
FIG. 9 is a schematic simulation diagram of a scenario of a target obstacle from a straight-ahead rear-end of a vehicle, according to one embodiment of the present invention;
FIG. 10 is a schematic analysis view of a collision of a target obstacle with a front side of a host vehicle when the host vehicle travels straight according to one embodiment of the present invention;
fig. 11 is a schematic analysis diagram of a collision of a target obstacle with a rear side of a host vehicle when the host vehicle travels straight according to one embodiment of the present invention;
fig. 12 is a schematic analysis diagram of a collision of a target obstacle with the left side of the own vehicle when the own vehicle travels straight, according to one embodiment of the present invention;
fig. 13 is a schematic analysis view of a collision of a target obstacle with the right side of the own vehicle when the own vehicle travels straight according to one embodiment of the present invention;
FIG. 14 is a schematic simulation diagram of a scenario in which a left turn target obstacle from a host vehicle is traveling straight, according to one embodiment of the present invention;
FIG. 15 is a schematic analysis diagram of a target obstacle colliding with a front side of a host vehicle when the host vehicle turns left according to one embodiment of the present invention;
FIG. 16 is a schematic analysis diagram of a target obstacle colliding with a rear side of a vehicle when the vehicle turns left according to one embodiment of the present invention;
FIG. 17 is a schematic analysis diagram of a target obstacle colliding with the left side of the host vehicle when the host vehicle turns left according to one embodiment of the present invention;
FIG. 18 is a schematic analysis diagram of a target obstacle colliding with the right side of the host vehicle when the host vehicle turns left according to one embodiment of the present invention;
fig. 19 is a schematic block diagram of a system for estimating a time to collision of a vehicle according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
Fig. 1 is a schematic flowchart of a method of estimating a time to collision of a vehicle according to an embodiment of the present invention, and fig. 2 is a schematic representation of an observation angle of a target obstacle with respect to a detection module according to an embodiment of the present invention. 1-2, in one particular embodiment, a method of estimating a time to collision for a vehicle may generally include the steps of:
s10, acquiring target obstacle information and coordinates of four vertex angles of the self-vehicle, wherein the target obstacle information comprises the type of a target obstacle and the observation angle and distance of the target obstacle relative to a detection module arranged on the self-vehicle;
s20, determining the expansion radius of the target obstacle according to the type of the target obstacle, wherein a plurality of circles with the same size are used for enveloping the target obstacle, the center of each circle is located on the longitudinal central axis of the target obstacle, and the minimum radius of each circle is taken as the expansion radius;
s30, calculating new coordinates of the four vertex angles of the bicycle after expansion treatment according to the coordinates and the expansion radius of the four vertex angles of the bicycle;
s40, converting the observation angle of the target obstacle relative to the detection module into an observation angle of a new coordinate relative to the four top corners of the vehicle according to the new coordinate of the four top corners of the vehicle;
s50, calculating initial expected collision time according to the observation angles of the new coordinates of the four top angles of the own vehicle;
and S60, judging whether the target barrier collides with the self vehicle according to the initial predicted collision time, and if so, calculating to obtain the final predicted collision time.
Here, the detection module records the observation angle of the detection module corresponding to the target obstacle at that time for all the detected target obstacles. The target obstacle i may be represented as
Figure BDA0002234453580000071
Set of target obstacles as
Figure BDA0002234453580000072
The invention can calculate the predicted collision time only by depending on the type of the target obstacle and the observation angle and the distance of the target obstacle relative to the detection module arranged on the self-vehicle, and has low dependence degree on the target obstacle and strong robustness. In addition, the invention can detect a plurality of target obstacles, and simultaneously calculate the predicted collision time for the plurality of target obstacles, thereby improving the safety of the vehicle.
S20 specifically includes the following steps:
the method comprises the following steps: searching size information of the target barrier corresponding to the type of the target barrier from a preset storage module according to the type of the target barrier, wherein the preset storage module stores the corresponding relation between the type of the target barrier and the size information in advance, and the type of the target barrier can be a vehicle or a person;
step two: calculating the expansion radius of the target obstacle according to the type and size information of the target obstacle, wherein the specific calculation formula is as follows:
Figure BDA0002234453580000081
where R is the expansion radius, W is the width of the target obstacle, L is the length of the target obstacle, and N is the number of circles determined according to the type of the target obstacle.
Fig. 3 is a schematic diagram of the relationship between the type of target obstacle and the expansion radius according to an embodiment of the present invention, as shown in fig. 3, and in particular, since the target obstacle detected by the detection module is a point, size information is lost with respect to a real obstacle. Whether the collision is inaccurate is judged only on the basis of the observation angle of the detection point, and the situation that the point track does not intersect with the self vehicle but the collision actually occurs exists. Therefore, the size of the vehicle subjected to the "inflation" process is considered when determining whether or not the vehicle will collide with the vehicle. The above problems can be solved to some extent.
The expansion radius of the self-vehicle is determined by the type of the target obstacle, and the specific volume and the size of the target obstacle are not detected and identified. For the main types of target obstacles encountered by a vehicle traveling on a road, the "expansion radius" is determined according to its category, without particularly depending on its size. Specific target obstacle types are as follows:
passenger car: n2, typical size (L4.7 m, W1.8 m), R1.48 m;
truck: n ═ 3, typical size (L ═ 8.2m, W ═ 2.5m), R ═ 1.85 m;
bicycle: n ═ 3, typical size (L ═ 1.7m, W ═ 0.45m), R ═ 0.36 m;
pedestrian: n ═ 1, typical dimensions (L ═ 0.45m, W ═ 0.24m), R ═ 0.26 m.
Fig. 4 is a schematic relationship diagram of the new coordinates of the four corners of the vehicle after expansion processing and the original coordinates according to an embodiment of the present invention, and as shown in fig. 4, the new coordinates of the four corners of the vehicle after expansion processing are calculated according to the coordinates of the four corners of the vehicle and the expansion radius, and the specific conversion is as follows:
pLF，pRF，pLR，pRRrespectively showing the left front top angle, the right front top angle, the left back top angle and the right back top angle of the bicycle. The detection module obtains the type of the target obstacle through detection, and determines the expansion radius R.
Changing the left front vertex angle of the bicycle to the coordinate of the coordinate system of the bicycle into (x)LF+R，yLF+ R), the observation angle for observing the target from the left front vertex angle is denoted as θLF。
Changing the coordinate of the right front vertex angle of the bicycle relative to the coordinate system of the bicycle into (x)RF+R，yRF-R), the observation angle of the object from the right front vertex angle is denoted θRF。
Changing the left back vertex angle of the bicycle to the coordinate of the coordinate system of the bicycle into (x)LR-R，yLR+ R), the observation angle for observing the target from the left back vertex angle is denoted as θLR。
Changing the right back vertex angle of the bicycle to the coordinate of the coordinate system of the bicycle into (x)RR-R，yRR-R), the observation angle of the object from the right back vertex angle is denoted θRR。
Further, the observation angle of the target obstacle relative to the detection module is converted into the observation angle of the new coordinate relative to the four top corners of the host vehicle according to the new coordinate of the four top corners of the host vehicle, and the specific conversion formula is as follows:
Figure BDA0002234453580000091
Xi＝dicosθi
Yi-disinθi；
wherein d isiIs the distance theta of the target obstacle relative to the detection moduleiIs the observation angle, X, of the target obstacle relative to the detection moduleiIs the abscissa, Y, of the target obstacle relative to the detection moduleiIs the ordinate, X, of the target obstacle relative to the detection module*The abscissa and Y are new coordinates of four vertex angles of the bicycle*Is the ordinate theta of the new coordinate of the four apex angles of the bicycle*And the observation angle of the target obstacle relative to the new coordinates of the four top corners of the self-vehicle is obtained.
Specifically, after converting the observation angle of the target obstacle relative to the detection module into an observation angle of a new coordinate relative to the four corners of the host vehicle according to the new coordinate of the four corners of the host vehicle, the method further includes:
and acquiring a plurality of observation angles of the target barrier corresponding to the new coordinates of the four vertex angles of the self vehicle at a plurality of moments in a preset time range.
Calculating initial predicted collision time according to the observation angles of new coordinates of the four top angles of the own vehicle, wherein the specific calculation formula is as follows:
Figure BDA0002234453580000092
wherein, t0For the current time, t is a time in the future,
Figure BDA0002234453580000093
the shortest time for fitting the observation angle of the target obstacle relative to the new coordinates of the four top corners of the self-vehicle to reach a preset time threshold value is obtained;
Ploy*(t) is a polynomial used to fit the observation angle, the polynomial being as follows:
Figure BDA0002234453580000094
a can be calculated according to a plurality of observation angles of the new coordinates of the target obstacle relative to the four top angles of the self vehicle corresponding to a plurality of moments in the preset time range3，a2，a1，a0；
Get PLF，PRF，PLR，PRRRespectively showing observation from a left front top corner, a right front top corner, a left rear top corner and a right rear top corner of the bicycle;
θΔfour characteristic observation angles of 90 degrees, -90 degrees, 0 degrees and 180 degrees are taken, the clockwise direction is negative, and the anticlockwise direction is positive.
Where if a solution does not exist it is recorded as positive infinity. In addition, for the same vertex angle, if
Figure BDA0002234453580000095
And
Figure BDA0002234453580000096
exist simultaneously, only the minimum value is kept; if it is
Figure BDA0002234453580000097
And
Figure BDA0002234453580000098
existing simultaneously, only the minimum value is preserved.
Further, the specific calculation formula may also be:
Figure BDA0002234453580000101
wherein, deltaΔThe value range is [ -30 DEG, 30 DEG ]]. Setting deltaΔIn order to take account of irregularities in the shape of the target obstacle and slight variations in the characteristic angle caused by projections from the front face, e.g. where δ may be takenΔ＝0°。
Fig. 5 is a schematic representation of a collision of a target obstacle with a front side of a host vehicle according to an embodiment of the present invention, fig. 6 is a schematic representation of a collision of a target obstacle with a left side of a host vehicle according to another embodiment of the present invention, fig. 7 is a schematic representation of a collision of a target obstacle with a right side of a host vehicle according to yet another embodiment of the present invention, and fig. 8 is a schematic representation of a collision of a target obstacle with a rear side of a host vehicle according to yet another embodiment of the present invention. As shown in fig. 5 to 8, in an embodiment, whether the target obstacle collides with the host vehicle is determined according to the initial predicted collision time, and if yes, the final predicted collision time is calculated, which specifically includes:
according to
Figure BDA0002234453580000102
Judging whether the target obstacle collides with the front side of the bicycle or not, if so
Figure BDA0002234453580000103
And
Figure BDA0002234453580000104
when the absolute value of the difference is less than a preset time threshold THS, it is determined that the target obstacle collides with the front side of the vehicle, that is
Figure BDA0002234453580000105
The final expected time to collision is
Figure BDA0002234453580000106
Andminimum value therebetween, i.e.
Figure BDA0002234453580000108
Otherwise, the automobile is not considered to collide with the front side of the automobile, and the collision time is recorded as positive infinity.
According to
Figure BDA0002234453580000109
Judging whether the target barrier collides with the left side of the vehicle when
Figure BDA00022344535800001010
And
Figure BDA00022344535800001011
when the absolute value of the difference is less than a preset time threshold THS, the target obstacle is judged to collide with the left side of the self-vehicle, namely the collision is judged
Figure BDA00022344535800001012
The final expected time to collision is
Figure BDA00022344535800001013
And
Figure BDA00022344535800001014
minimum value therebetween, i.e.
Figure BDA00022344535800001015
Otherwise, the automobile is not considered to collide with the left side of the automobile, and the collision time is recorded as positive infinity.
The final expected time to collision is
Figure BDA00022344535800001016
And
Figure BDA00022344535800001017
minimum value therebetween, i.e.
Figure BDA00022344535800001018
In another embodiment, whether the target obstacle collides with the host vehicle is determined according to the initial predicted collision time, and if so, the final predicted collision time is calculated, and the method specifically includes:
according to
Figure BDA00022344535800001019
Judging whether the target barrier collides with the right side of the vehicle when
Figure BDA00022344535800001020
And
Figure BDA00022344535800001021
when the absolute value of the difference is less than a preset time threshold THS, the target obstacle is judged to collide with the right side of the self-vehicle, namely the collision is judged
Figure BDA00022344535800001022
The final expected time to collision is
Figure BDA00022344535800001023
And
Figure BDA00022344535800001024
minimum value therebetween, i.e.
Figure BDA0002234453580000111
Otherwise, the collision is not considered to be from the right side, and the collision time is recorded as positive infinity.
According toJudging whether the target barrier collides with the tail side of the vehicle or not, if so
Figure BDA0002234453580000113
And
Figure BDA0002234453580000114
when the absolute value of the difference is less than a preset time threshold THS, the target obstacle is judged to collide with the tail side of the vehicle, namely the target obstacle collides with the tail side of the vehicleThe final expected time to collision is
Figure BDA0002234453580000116
Andminimum value therebetween, i.e.
Figure BDA0002234453580000118
Otherwise, the automobile is not considered to collide with the tail side of the automobile, and the collision time is recorded as positive infinity.
The final expected time to collision isMinimum value therebetween, i.e.
Figure BDA00022344535800001110
In the running process of the vehicle, the invention can utilize the information of the target barrier and the state information of the vehicle provided by the detection device to correctly screen the target with collision threat as early as possible, and comprehensively considers the predicted time of the collision between the target barrier and the periphery of the vehicle, screens the earliest time of the collision between the target barrier and the vehicle in advance, thereby improving the driving safety.
The invention can calculate the collision time of a plurality of target collision objects and the self-vehicle at the same time, wherein the smaller the calculated collision time is, the higher the collision risk is. The invention can screen out the targets which are likely to collide with the own vehicle, sort according to the estimated collision time, estimate that the smaller the collision time, the higher the priority, and then process the targets with high collision risk according to the priority level.
Fig. 9 is a schematic simulation diagram of a scene in which an own vehicle directly travels to rear-end a target obstacle according to an embodiment of the present invention, fig. 10 is a schematic analysis diagram of a collision of the target obstacle with the front side of the own vehicle when the own vehicle directly travels according to an embodiment of the present invention, fig. 11 is a schematic analysis diagram of a collision of the target obstacle with the rear side of the own vehicle when the own vehicle directly travels according to an embodiment of the present invention, fig. 12 is a schematic analysis diagram of a collision of the target obstacle with the left side of the own vehicle when the own vehicle directly travels according to an embodiment of the present invention, and fig. 13 is a schematic analysis diagram of a collision of the target obstacle with the right side of the own vehicle when the own vehicle directly travels according to an embodiment of the present invention. At the time when t is 4s in fig. 9, collision between the vehicle front side and the target obstacle is predicted. Simulation verification can also be performed through fig. 10-13, and fig. 10-13 show the simulation effect of the method of the present invention, and prediction analysis is performed on the time when the collision occurs on the front side, the rear side, the left side and the right side of the vehicle when t is 4 s. The method mainly comprises the steps of carrying out polynomial fitting on the trend of four vertex angles of a self-vehicle relative to an observation angle of a target obstacle, predicting the collision time corresponding to the observation angle by using the fitted polynomial, and considering that the collision will occur if the collision time of two vertexes corresponding to the side surface of the self-vehicle is relatively close. As shown in fig. 10 to 13, it can be seen that the front side of the vehicle will collide with the target obstacle according to the prediction of the observation angle.
It should be noted that, the simulation result does not consider the influence of factors such as noise and FOV of the detection device, and does not consider the shielding and shielding of the target obstacle, that is, all target obstacles in the scene can be accurately detected and tracked.
Fig. 14 is a schematic simulation diagram of a scene in which a left turn target obstacle of an own vehicle travels straight according to an embodiment of the present invention, fig. 15 is a schematic analysis diagram of a collision of the target obstacle with the front side of the own vehicle when the own vehicle turns left according to an embodiment of the present invention, fig. 16 is a schematic analysis diagram of a collision of the target obstacle with the rear side of the own vehicle when the own vehicle turns left according to an embodiment of the present invention, fig. 17 is a schematic analysis diagram of a collision of the target obstacle with the left side of the own vehicle when the own vehicle turns left according to an embodiment of the present invention, and fig. 18 is a schematic analysis diagram of a collision of the target obstacle with the right side of the own vehicle when the own vehicle turns left according to an embodiment of the present invention. At the time when t is 4s in fig. 14, collision between the vehicle front side and the target obstacle is predicted. Simulation verification can also be performed through fig. 15-18, and fig. 15-18 show the simulation effect of the method of the present invention, and prediction analysis is performed on the time when the collision occurs on the front side, the rear side, the left side and the right side of the vehicle when t is 4 s. The method mainly comprises the steps of carrying out polynomial fitting on the trend of four vertex angles of a self-vehicle relative to an observation angle of a target obstacle, predicting the collision time corresponding to the observation angle by using the fitted polynomial, and considering that the collision will occur if the collision time of two vertexes corresponding to the side surface of the self-vehicle is relatively close. As shown in fig. 15 to 18, it can be seen that the front side of the vehicle will collide with the target obstacle according to the prediction of the observation angle.
Fig. 19 is a schematic block diagram of a system for estimating a time to collision of a vehicle according to an embodiment of the present invention. As shown in fig. 19, the present invention further provides a system applied to the method for predicting the time of collision of a vehicle in any of the above embodiments, which includes a detection module 10 and a calculation module 20. The detection module 10 is arranged on the self-vehicle and used for acquiring target obstacle information and coordinates of four top corners of the self-vehicle, and the detection module 10 is further used for acquiring a plurality of observation angles of the target obstacle corresponding to a plurality of moments in a preset time range relative to new coordinates of the four top corners of the self-vehicle to calculate and obtain final predicted collision time. The calculation module 20 calculates the final expected collision time according to the received target obstacle information, the coordinates of the four corners of the vehicle and a plurality of observation angles of the target obstacle corresponding to a plurality of moments relative to the new coordinates of the four corners of the vehicle.
The invention also provides a vehicle which is provided with the system. For the system, it is not repeated here.
Thus, it should be appreciated by those skilled in the art that while a number of exemplary embodiments of the invention have been illustrated and described in detail herein, many other variations or modifications consistent with the principles of the invention may be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Accordingly, the scope of the invention should be understood and interpreted to cover all such other variations or modifications.

Claims (10)

1. A method of predicting a time to collision for a vehicle, comprising:
acquiring target obstacle information and coordinates of four vertex angles of a self vehicle, wherein the target obstacle information comprises the type of a target obstacle and the observation angle and distance of the target obstacle relative to a detection module arranged on the self vehicle;
determining the expansion radius of the target obstacle according to the type of the target obstacle, wherein a plurality of circles with the same size are used for enveloping the target obstacle, the center of each circle is located on the longitudinal central axis of the target obstacle, and the minimum radius of each circle is taken as the expansion radius;
calculating new coordinates of the four vertex angles of the self-vehicle after expansion treatment according to the coordinates of the four vertex angles of the self-vehicle and the expansion radius;
converting the observation angle of the target obstacle relative to the detection module into an observation angle of a new coordinate relative to the four top corners of the vehicle according to the new coordinate of the four top corners of the vehicle;
calculating initial expected collision time according to the observation angles of the new coordinates of the four top angles of the self-vehicle;
and judging whether the target barrier collides with the self vehicle or not according to the initial predicted collision time, and if so, calculating to obtain the final predicted collision time.
2. The method according to claim 1, wherein determining the expansion radius of the target obstacle according to the type of the target obstacle comprises:
searching size information of the target obstacle corresponding to the type of the target obstacle from a preset storage module according to the type of the target obstacle, wherein the preset storage module stores the corresponding relation between the type of the target obstacle and the size information in advance, and the type of the target obstacle is a vehicle or a person;
calculating the expansion radius of the target obstacle according to the type of the target obstacle and the size information, wherein a specific calculation formula is as follows:
Figure FDA0002234453570000011
wherein R is an expansion radius, W is a width of the target obstacle, L is a length of the target obstacle, and N is the number of circles determined according to the type of the target obstacle.
3. The method according to claim 1, wherein the observation angle of the target obstacle relative to the detection module is converted into the observation angle relative to the new coordinates of the four corners of the host vehicle according to the new coordinates of the four corners of the host vehicle, and the specific conversion formula is as follows:
Figure FDA0002234453570000021
Xi＝dicos θi
Yi＝disin θi；
wherein d isiIs the distance theta of the target obstacle relative to the detection moduleiIs the observation angle, X, of the target obstacle relative to the detection moduleiIs the abscissa, Y, of the target obstacle relative to the detection moduleiIs the ordinate, X, of the target obstacle relative to the detection module*The abscissa and Y are new coordinates of four vertex angles of the bicycle*Is the ordinate theta of the new coordinate of the four apex angles of the bicycle*And the observation angle of the target obstacle relative to the new coordinates of the four top corners of the self-vehicle is obtained.
4. The method of claim 3, further comprising, after converting the observation angle of the target obstacle relative to the detection module from the new coordinates of the four corners of the host vehicle to an observation angle relative to the new coordinates of the four corners of the host vehicle:
and acquiring a plurality of observation angles of the target obstacle corresponding to new coordinates of four vertex angles of the self vehicle at a plurality of moments within a preset time range.
5. The method as claimed in claim 4, wherein the initial predicted collision time is calculated according to the observation angle of the new coordinates of the four top corners of the own vehicle, and the specific calculation formula is as follows:
Figure FDA0002234453570000022
wherein, t0For the current time, t is a time in the future,the shortest time for fitting the observation angle of the target obstacle relative to the new coordinates of the four top corners of the self-vehicle to reach a preset time threshold value is obtained;
Ploy*(t) is a polynomial used to fit the observation angle, the polynomial being as follows:
a is obtained by calculating a plurality of observation angles of the target obstacle corresponding to the new coordinates of the four top angles of the self vehicle at a plurality of moments in the preset time range3，a2，a1，a0；
Get PLF，PRF，PLR，PRRRespectively showing observation from a left front top corner, a right front top corner, a left rear top corner and a right rear top corner of the bicycle;
θΔfour characteristic observation angles of 90 degrees, -90 degrees, 0 degrees and 180 degrees are taken, the clockwise direction is negative, and the anticlockwise direction is positive.
6. The method as claimed in claim 5, wherein the initial predicted collision time is calculated according to the observation angle of the new coordinates of the four top corners of the host vehicle, and the specific calculation formula is further as follows:
Figure FDA0002234453570000031
wherein, deltaΔThe value range is [ -30 DEG, 30 DEG ]]。
7. The method according to claim 6, wherein determining whether the target obstacle collides with the host vehicle according to the initial predicted collision time, and if so, calculating a final predicted collision time, specifically comprising:
according to
Figure FDA0002234453570000032
Judging whether the target barrier collides with the front side of the bicycle or not, and if so, judging whether the target barrier collides with the front side of the bicycle
Figure FDA0002234453570000033
And
Figure FDA0002234453570000034
when the absolute value of the difference is less than a preset time threshold value, the target obstacle is judged to collide with the front side of the vehicle, and the time for predicting the collision with the front side of the vehicle is
Figure FDA0002234453570000035
And
Figure FDA0002234453570000036
minimum value therebetween, i.e.
Figure FDA0002234453570000037
According to
Figure FDA0002234453570000038
Judging whether the target barrier collides with the left side of the self-vehicle or not, and judging whether the target barrier collides with the left side of the self-vehicle or not when the target barrier collides with the left side of the self-vehicle
Figure FDA0002234453570000039
And
Figure FDA00022344535700000310
when the absolute value of the difference is smaller than the preset time threshold value, the target barrier is judged to collide with the left side of the self-vehicle, and the predicted time for colliding with the left side of the self-vehicle is
Figure FDA00022344535700000311
And
Figure FDA00022344535700000312
minimum value therebetween, i.e.
Figure FDA00022344535700000313
The final expected time to collision is
Figure FDA00022344535700000314
And
Figure FDA00022344535700000315
minimum value therebetween, i.e.
Figure FDA00022344535700000316
8. The method according to claim 7, wherein whether the target obstacle collides with the host vehicle is determined according to the initial predicted collision time, and if so, a final predicted collision time is calculated, and the method further comprises:
according to
Figure FDA00022344535700000317
Judging whether the target barrier collides with the right side of the vehicle or not, and judging whether the target barrier collides with the right side of the vehicle or not
Figure FDA00022344535700000318
And
Figure FDA00022344535700000319
when the absolute value of the difference is smaller than the preset time threshold value, the target barrier is judged to collide with the right side of the self-vehicle, and the predicted time for colliding with the right side of the self-vehicle is
Figure FDA00022344535700000320
And
Figure FDA00022344535700000321
minimum value therebetween, i.e.
Figure FDA00022344535700000322
According to
Figure FDA00022344535700000323
Judging whether the target barrier collides with the tail side of the vehicle or not, and if so, judging whether the target barrier collides with the tail side of the vehicle
Figure FDA00022344535700000324
And
Figure FDA00022344535700000325
when the absolute value of the difference is smaller than the preset time threshold value, the target obstacle is judged to collide with the tail side of the vehicle, and the time for collision with the tail side of the vehicle is estimated to be
Figure FDA00022344535700000326
And
Figure FDA00022344535700000327
the most between the twoSmall value, i.e.
Figure FDA00022344535700000328
The final expected time to collision isMinimum value therebetween, i.e.
Figure FDA0002234453570000041
9. A system applied to the method for estimating the time of collision of the vehicle as claimed in any one of claims 1 to 8, characterized by comprising a detection module and a calculation module,
the detection module is arranged on the self-vehicle and used for acquiring the information of the target obstacle and coordinates of four top corners of the self-vehicle, and the detection module is also used for acquiring a plurality of observation angles of the target obstacle corresponding to new coordinates of the four top corners of the self-vehicle at a plurality of moments within a preset time range;
and the calculation module is used for calculating the final predicted collision time according to the received target obstacle information, the coordinates of the four top corners of the vehicle and a plurality of observation angles of the target obstacle corresponding to the new coordinates of the four top corners of the vehicle at a plurality of moments.
10. A vehicle, characterized in that the vehicle is equipped with a system according to claim 9.
CN201910978601.2A 2019-10-15 2019-10-15 Method and system for predicting collision time of vehicle and vehicle Active CN110696823B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910978601.2A CN110696823B (en) 2019-10-15 2019-10-15 Method and system for predicting collision time of vehicle and vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910978601.2A CN110696823B (en) 2019-10-15 2019-10-15 Method and system for predicting collision time of vehicle and vehicle

Publications (2)

Publication Number Publication Date
CN110696823A true CN110696823A (en) 2020-01-17
CN110696823B CN110696823B (en) 2020-12-18

Family

ID=69199616

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910978601.2A Active CN110696823B (en) 2019-10-15 2019-10-15 Method and system for predicting collision time of vehicle and vehicle

Country Status (1)

Country Link
CN (1) CN110696823B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111591288A (en) * 2020-03-31 2020-08-28 北京智行者科技有限公司 Collision detection method and device based on distance transformation graph
CN112015181A (en) * 2020-08-28 2020-12-01 上海高仙自动化科技发展有限公司 Obstacle avoidance method, device, equipment and computer readable storage medium
CN112572472A (en) * 2020-12-08 2021-03-30 重庆大学 Automatic driving collision prediction method based on Frenet coordinate system
CN113928340A (en) * 2021-10-26 2022-01-14 中国第一汽车股份有限公司 Obstacle avoidance method and device applied to vehicle, electronic equipment and storage medium
CN114261389A (en) * 2021-11-29 2022-04-01 东风商用车有限公司 Running track collision risk analysis method of automatic driving commercial vehicle
CN114379545A (en) * 2020-10-16 2022-04-22 上海汽车集团股份有限公司 Vehicle anti-collision method and device
DE102021109661A1 (en) 2021-04-16 2022-10-20 Avl Software And Functions Gmbh Method for the geometric representation of a vehicle surface of a vehicle for collision detection
CN115629612A (en) * 2022-12-19 2023-01-20 科大讯飞股份有限公司 Obstacle avoidance method, device, equipment and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060178830A1 (en) * 2005-02-10 2006-08-10 Rini Sherony Vehicle collision warning system
EP3236426A1 (en) * 2016-04-20 2017-10-25 Cf3000 - S.R.L. Remote testing system for a vehicle
CN108775902A (en) * 2018-07-25 2018-11-09 齐鲁工业大学 The adjoint robot path planning method and system virtually expanded based on barrier
CN109141441A (en) * 2018-07-19 2019-01-04 北京汽车集团有限公司 The obstacle analysis method and apparatus of vehicle

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060178830A1 (en) * 2005-02-10 2006-08-10 Rini Sherony Vehicle collision warning system
EP3236426A1 (en) * 2016-04-20 2017-10-25 Cf3000 - S.R.L. Remote testing system for a vehicle
CN109141441A (en) * 2018-07-19 2019-01-04 北京汽车集团有限公司 The obstacle analysis method and apparatus of vehicle
CN108775902A (en) * 2018-07-25 2018-11-09 齐鲁工业大学 The adjoint robot path planning method and system virtually expanded based on barrier

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111591288B (en) * 2020-03-31 2021-09-10 北京智行者科技有限公司 Collision detection method and device based on distance transformation graph
CN111591288A (en) * 2020-03-31 2020-08-28 北京智行者科技有限公司 Collision detection method and device based on distance transformation graph
CN112015181A (en) * 2020-08-28 2020-12-01 上海高仙自动化科技发展有限公司 Obstacle avoidance method, device, equipment and computer readable storage medium
CN112015181B (en) * 2020-08-28 2021-08-10 上海高仙自动化科技发展有限公司 Obstacle avoidance method, device, equipment and computer readable storage medium
CN114379545B (en) * 2020-10-16 2024-02-02 上海汽车集团股份有限公司 Anti-collision method and device for vehicle
CN114379545A (en) * 2020-10-16 2022-04-22 上海汽车集团股份有限公司 Vehicle anti-collision method and device
CN112572472A (en) * 2020-12-08 2021-03-30 重庆大学 Automatic driving collision prediction method based on Frenet coordinate system
DE102021109661A1 (en) 2021-04-16 2022-10-20 Avl Software And Functions Gmbh Method for the geometric representation of a vehicle surface of a vehicle for collision detection
US11975711B2 (en) 2021-04-16 2024-05-07 Avl Software And Functions Gmbh Method for the geometric representation of a vehicle area of a vehicle for the purpose of collision detection
DE102021109661B4 (en) 2021-04-16 2023-03-09 Avl Software And Functions Gmbh Method for the geometric representation of a vehicle surface of a vehicle for collision detection
CN113928340A (en) * 2021-10-26 2022-01-14 中国第一汽车股份有限公司 Obstacle avoidance method and device applied to vehicle, electronic equipment and storage medium
CN113928340B (en) * 2021-10-26 2024-05-03 中国第一汽车股份有限公司 Obstacle avoidance method and device applied to vehicle, electronic equipment and storage medium
CN114261389A (en) * 2021-11-29 2022-04-01 东风商用车有限公司 Running track collision risk analysis method of automatic driving commercial vehicle
CN114261389B (en) * 2021-11-29 2023-05-12 东风商用车有限公司 Driving track collision risk analysis method for automatic driving commercial vehicle
CN115629612A (en) * 2022-12-19 2023-01-20 科大讯飞股份有限公司 Obstacle avoidance method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN110696823B (en) 2020-12-18

Similar Documents

Publication Publication Date Title
CN110696823B (en) Method and system for predicting collision time of vehicle and vehicle
US9784829B2 (en) Wheel detection and its application in object tracking and sensor registration
JP3846494B2 (en) Moving obstacle detection device
CN109891262B (en) Object detecting device
WO2017014080A1 (en) Driving assistance system
US20130179047A1 (en) Intersection collision avoidance with adaptable vehicle dimensions
JP5846109B2 (en) Collision determination device and collision avoidance system
WO2010064282A1 (en) Pre-crash safety system
JP2019093764A (en) Vehicle control device
US20210316734A1 (en) Vehicle travel assistance apparatus
JP5083172B2 (en) Collision prediction device
US10970870B2 (en) Object detection apparatus
US11420624B2 (en) Vehicle control apparatus and vehicle control method
CN113511198B (en) Method, apparatus and storage medium for predicting blind zone collision when self-vehicle turns
US10144418B2 (en) Control apparatus for vehicle
US20230034560A1 (en) Method for tracking a remote target vehicle in an area surrounding a motor vehicle by means of a collision detection device
CN112950999A (en) Automobile early warning method and device, electronic equipment and storage medium
CN107139922B (en) Automobile rear-end collision prevention method
CN114466776A (en) Vehicle control method, vehicle control device, and vehicle control system including the vehicle control device
EP4052068A1 (en) Systems and methods of geometric vehicle collision evaluation
CN108885833A (en) Vehicle checking device
KR102335987B1 (en) Apparatus and method for drive controlling of vehicle
CN113022593B (en) Obstacle processing method and device and traveling equipment
US11667295B2 (en) Apparatus and method for recognizing object
CN112061118B (en) Vehicle collision prediction method and device

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