Method and apparatus of predicting collision for omnidirectional application within emergency brake system

Abstract

A method and an apparatus for predicting a collision are provided. The method includes calculating, by a controller, a driving trajectory of the subject vehicle based on a yaw rate using driving information of the subject vehicle. In addition, the controller is configured to calculate a driving trajectory of a target vehicle for a predetermined period of time that uses driving information of the target vehicle that includes information from an imaging device, configured to obtain a front image, and radar sensors installed on a plurality of locations. Further, the method also includes predicting classified collision types by analyzing a collision possibility between the subject vehicle and the target vehicle based on the driving trajectory of the subject vehicle and the driving trajectory of the target vehicle.

Description

CROSS-REFERENCE TO RELATED APPLICATION

This application
y(k+1)=y(k)+v(k)sin ψ(k)Δt
v(k+1)=v_x(k)+αΔt
ψ(k+1)=ψ(k)+γΔt   Equation 3

According to the present disclosure, a complex motion of the target vehicle may be predicted by subdividing the location of the target vehicle into the predetermined period of time to predict a collision. Further, a system that may be configured to calculate the tracking information (TTX) such as the predefined time-to-intersect and time-to-exit related information (e.g., TTI, TTE, TTAI, TTAE, TTC, and the like) of the target vehicle may be more easily designed.

The tracking information (TTX) calculating unit 122 may be configured to calculate time-to-intersect and time-to-exit related tracking information (TTX) of the target vehicle such as a time-to-intersect (TTI), a time-to-exit (TTE), a time-to-angular-intersect (TTAI), a time-to-angular-exit (TTAE), a time-to-collision (TTC), and the like, which may be predefined, using the driving trajectory of the target vehicle and the driving trajectory of the subject vehicle. In other words, the tracking information (TTX) calculating unit 122 may be configured to calculate the tracking information (TTX), which may be related to a time when the target vehicle intersects with or exits from the driving trajectory of the subject vehicle during the predetermined period of time (e.g., three seconds).

The time-to-intersect (TTI) may be a time when a portion of the target vehicle intersects with a path of the driving trajectory of the subject vehicle, and FIG. 3 illustrates an exemplary embodiment of the TTI when a crossing vehicle (e.g., a target vehicle) begins to enter the path of the driving trajectory of the subject vehicle. The time-to-exit (TTE) may be a time when the target vehicle (e.g., from a front of a target vehicle to a rear of the target vehicle) exits from the path of the driving trajectory of the subject vehicle, and FIG. 3 illustrates an exemplary embodiment of the TTE when a crossing vehicle (e.g., a target vehicle) passes through and exits from the path of the driving trajectory of the subject vehicle.

The time-to-angular-intersect (TTAI) may be a time when a portion of the target vehicle intersects with a circular trajectory of the subject vehicle based on a substantially center point of the curvature radius R of the driving trajectory of the subject vehicle, and FIG. 3 illustrates an exemplary embodiment of the TTAI when a front vehicle, a crossing vehicle, an oncoming vehicle, a rear vehicle, and the like begin to enter the path of the circular trajectory of the subject vehicle at the same angle. The time-to-angular-exit (TTAE) may be a time when the entire target vehicle (e.g., the whole vehicle from the front end to the rear end) exits from the circular trajectory of the subject vehicle based on the center point of the curvature radius R of the driving trajectory of the subject vehicle, and FIG. 3 illustrates an exemplary embodiment of the TTAE when a front vehicle, a crossing vehicle, an oncoming vehicle, a rear vehicle, and the like pass through the location of the subject vehicle on the circular trajectory of the subject vehicle and exit from the location of the subject vehicle at about the same angle.

The time-to-collision (TTC) may be a timing-to-collision when a collision with a front vehicle, a crossing vehicle, an oncoming vehicle, a rear vehicle, and the like is expected. For example, the time-to-collision (TTC) may be when condition 2 or condition 3 occurs and condition 1 is satisfied.

Condition 1

(TTI<TTAE) and (TTAI<TTE)

Condition 2

Any one point (e.g., a vertex) of the target vehicle, at which the intersection or the angular-intersection occurs, is the same location as the portion of the subject vehicle.
(L|cos θ sin θ|)−(|G sin θ|+|α cos θ|)<0   Condition 3

When TTI is less than TTAE as described in condition 1, the intersection may occur before the target vehicle 20 angularly-exits from the circular driving trajectory of the subject vehicle 10. At the same time, when TTAI is less than TTE (e.g., when the angular-intersect occurs before the target vehicle 20 exits from the driving trajectory of the subject vehicle 10), a collision may be expected. However, when condition 1 is satisfied, the subject vehicle 10 and the target vehicle 20 may be prevented from colliding. For example, FIG. 4 shows TTI is less than TTAE since TTI may equal 0 and TTAI is less than TTE since TTAI may be greater than equal 0, but the collision may be prevented. Therefore, when condition 1 is satisfied, the collision may be expected when any point (e.g., a vertex) of the target vehicle 20 is in the same location as the portion of the subject vehicle 10.

In addition, when the condition 1 is satisfied, as shown in FIG. 5, and condition 3 is satisfied, a collision may be expected. In condition 3, L may represent about the entire length from a front of the target vehicle 20 to the rear of the target vehicle 20, G may represent a front intersecting length after the target vehicle 20 angularly-intersects, α may represent a rear intersecting length in the driving path direction of the target vehicle 20, and θ may represent an angle between a driving direction of the subject vehicle 10 and a driving direction of the target vehicle 20.

Further, when acceleration/deceleration, the tracking information (TTX) calculating unit 122 may be configured to calculate the TTI when the subject vehicle decelerates (TTI_d) and the TTE when the subject vehicle accelerates (TTE_a) to predict whether the collision will occur based on the acceleration/deceleration of the subject vehicle. In Equation 4, TTI_max may represent a predetermined maximum value of the TTI, TTE_max may represent a predetermined maximum value of the TTE, a_decel may represent acceleration when the subject vehicle decelerates, a_accel may represent acceleration when the subject vehicle accelerates, v_t may represent a velocity when the subject vehicle starts to accelerate or decelerate, and a_t may represent acceleration after starting the acceleration or deceleration of the subject vehicle.

The TTI when the subject vehicle decelerates (TTI_d) may increase relative to an original TTI based on a deceleration degree, and when the deceleration of the subject vehicle is greater than a predetermined value, the subject vehicle may stop before an intersection (e.g., the subject vehicle and a target vehicle collide) occurs, thereby creating a non-collision situation. Accordingly, the TTI_d may be replaced with the predetermined maximum value (TTI_max) of the TTI as in Equation 4, and since the location prediction may be performed up to about 3 seconds, for example, the TTI_max may be set to a value of about 3 seconds or greater.

The TTE the subject vehicle accelerates (TTE_a) may be decreased relative to an original TTE based on the acceleration, and when the exit from the path of the driving trajectory of the subject vehicle is not scheduled (e.g., when the acceleration of the subject vehicle is less than a predetermined value), the TTE_a may be the maximum value (TTE_max).

$\begin{array}{cc}{\mathrm{TTI}}_d=\{\begin{array}{c}{\mathrm{TTI}}_{\max }-\frac{v_t^2}{2\left(v_t\mathrm{TTI}+a_t{\mathrm{TTI}}^2\right)}-a_{\mathrm{decel}}=>0\\ -\frac{v_i-\sqrt{v_t^2+2\frac{\left(v_t\mathrm{TTI}+a_t{\mathrm{TTI}}^2\right)}{a_{\mathrm{decel}}}}}{a_{\mathrm{decel}}},\\ -\frac{v_t^2}{2\left(v_t\mathrm{TTI}+a_t{\mathrm{TTI}}^2\right)}-a_{\mathrm{decel}}<0\end{array}{\mathrm{TTE}}_a=\{\begin{array}{c}{\mathrm{TTE}}_{\max },\mathrm{TTE}={\mathrm{TTE}}_{\max }\\ \frac{v_t-\sqrt{v_t^2+2\frac{\left(v_t\mathrm{TTE}+a_t{\mathrm{TTE}}^2\right)}{a_{\mathrm{accel}}}}}{a_{\mathrm{accel}}},\mathrm{TTE}<{\mathrm{TTE}}_{\max }\end{array}& \mathrm{Equation}4\end{array}$

In FIG. 2, the collision determining unit 123 may be configured to determine various collision types for a front vehicle, a crossing vehicle, an oncoming vehicle, a rear vehicle, and the like by predicting, collision flags. The collision flags may be classified in advance based conditions that use the time-to-intersect and time-to-exit related tracking information (TTX) of the target vehicle.

FIG. 6 is an exemplary conditional table for predicting whether a collision between the subject vehicle and the target vehicle occurs based on the time-to-intersect and time-to-exit related tracking information (TTX). FIG. 6 is summarized in a way where the TTX may increase in a right direction, and may classify a case when the collision is detected or is imminent into ‘Collision’, a case when a collision may be avoided into ‘Avoidable’, a case when a target (e.g., target vehicle) is not present or a situation is not detected into ‘Avoided’, and the like. Even when condition 1, condition 2, or condition 3 are satisfied, whether the collision may occur may be more accurately determined based on the conditions such as the TTI_d, the TTE_a, and the like.

As illustrated in FIG. 6, when the TTI and the TTAI are substantially small or the TTE and the TTAE are substantially large, a collision probability may be increased, and the collision determining unit 123 may be configured to determine the collision flags as illustrated in FIG. 7 based on a time difference between the TTI and the TTAE and a time difference between the TTAI and the TTE. For example, ‘Avoided’ cases, when the target (e.g., the target vehicle) is not present or the situation is not detected, may correspond to collision flags 0 and 1 as shown in FIG. 7 based on the time difference between the TTI and the TTAE and the time difference between the TTAI and the TTE. In addition, ‘Avoidable’ cases, when the collision may be avoided as shown in FIG. 6, may correspond to collision flags 2 to 5 based on the time difference between the TTI and the TTAE and the time difference between the TTAI and the TTE.

Further, ‘Collision’ cases, when the collision is detected or is imminent (e.g., when the collision may occur within a predetermined period of time) may correspond to the collision flags 6 to 8. For the predictions as described above, a collision direction, and the like, which may be predicted by a location and a direction of the time-to-collision (TTC) with the target vehicle, may be referenced in addition to the TTC, the driving information of the subject vehicle (e.g., the velocity, the acceleration, and the like of the subject vehicle), the driving trajectory of the subject vehicle, and the driving trajectory of the target vehicle, which may be analyzed by the target path predicting unit 121, and the like may be referenced.

FIG. 8 is an exemplary flow chart showing a collision type prediction by the collision determining unit according to an exemplary embodiment of the present disclosure. Referring to FIG. 8, the collision determining unit 123 may be configured to predict collision flags 0 to 5 (S11) as a non-collision (e.g., a collision type 0), determine various collision types for a front vehicle, a crossing vehicle, an oncoming vehicle, a rear vehicle, and predict a collision direction using a location and a direction of a collision timing with the predicted target vehicle for the collision flags 6 to 8 (S10). As illustrated in FIG. 9, the respective collision types may be determined based on whether the target vehicle exits from the path of the driving trajectory of the subject vehicle, the collision direction, or the like. Particularly, in FIG. 9, collision types 3 and 4 may have the same collision direction, but may be classified differently based on whether the other target vehicle exits from the driving trajectory path of the subject vehicle, one collision type may correspond to collision type 3, and another collision type may correspond to collision type 4.

Collision type 4 may be when the oncoming vehicle is expected to arrive at a current location of the subject vehicle, and collision avoidance is impossible by a longitudinal motion of the subject vehicle. Alternatively, collision type 3 may be the same front-front collision as the collision type 4, but may be when the subject vehicle may avoid the collision. For the predictions as described above, a collision direction, and the like, which may be predicted by a location and a direction of the time-to-collision (TTC) with the target vehicle, may be referenced. Further, the path of the driving trajectory of the target vehicle, which may be analyzed by the target path predicting unit 121, and the like may be referenced.

In FIG. 8, for collision flags 6 to 8, when TTI is less greater than TTAI (S20) may be when an angular-intersection is expected, and may be correspond to collision type 5 when a collision between a side rear (e.g., a rear side of a side a vehicle) of the subject vehicle and a front of the target vehicle may be expected (S21).

In addition, when TTI is less than TTAI, the collision with the other target vehicle of the front, the side, or the rear may be expected as follows. In other words, the crossing collisions (e.g., collision types 2, 3, and 5) with a crossing vehicle, the collision (e.g., collision type 4) with an oncoming vehicle, the rear collision (e.g., collision type 6) with a rear vehicle, a second rear collision (e.g., collision type 1), and the like may occur. When the collision type does not correspond to the above-mentioned types, a non-classification may be determined.

For example, when a collision (e.g., rear-front collision) between the rear or the side rear of the subject vehicle and the front of the other target vehicle is predicted (S30) in FIG. 8, when the TTE is a predetermined time (e.g., about 3 seconds) or greater (S31), the collision type may be predicted as the rear collision (the collision type 6) with the rear vehicle (S32). However, when the TTE is less than the predetermined time (e.g., about 3 seconds) (S31), which is when the angular-intersect is expected, the collision type may be predicted to be collision type 5 in which the collision between the side rear (rear of side) of the subject vehicle and the front of the crossing vehicle which is the other target vehicle, that is, the crossing, collision (side rear-front) is expected (S33).

In addition, when a collision (e.g., front-front collision) between the front of the subject vehicle and the front of the other target vehicle is predicted (S40) and the collision may not be avoided (S41), the collision type may be predicted to correspond to a front-front collision (e.g., collision type 4) with the oncoming vehicle (S42). In particular, when the collision may be avoided (S41), the collision type may correspond to a front-front collision (e.g., collision type 3) (S43).

Further, when a collision (e.g., front-rear collision) between the front of the subject vehicle and the rear or the side rear of the target vehicle is predicted (S50) and the TTE is the predetermined period of time (e.g., about 3 seconds) or greater (S51), the collision type may be predicted as a rear collision (e.g., collision type 1) where the subject vehicle collides into the target vehicle (S52). However, when the TTE is less than the predetermined period of time (e.g., three seconds) (S51), the collision type may be predicted to correspond to the collision between the front of the subject vehicle and the side rear of the target vehicle (e.g., collision type 2) (S53).

Furthermore, when a collision between the side rear (e.g., a rear side of a side of a vehicle) of the subject target vehicle and the side front of the target subject vehicle is predicted (S60) and the TTI is less than the TTAI for collision flags 6 to 8, the collision type may be predicted to correspond to collision type 2 (S61).

As described above, the apparatus 100 for predicting a collision may more easily avoid collisions by expanding the prediction of collisions to the vehicles in an omni-direction (e.g., about 360 degrees) within an emergency brake system such as an advanced emergency brake (AEB) system. For example, the apparatus 100 may accurately perform a brake related control based on models of the collision vehicles or the collision types, or may perform an airbag related control (e.g., an unfolding of the airbag, a preparation of the unfolding, or the like) in advance.

In addition the apparatus 100 may be applied to an adaptive cruise control system (ACCS), a forward vehicle collision avoidance system (FVCAS), a side and backward vehicle collision avoidance system (SBVCAS), a lane departure warning system (LDWS), and the like. Further, according to the exemplary embodiments of the present disclosure, the method and the apparatus of predicting the collision emergency may avoid collision by expanding the prediction of a collision to vehicles in an omni-direction (e.g., about 360 degree).

Hereinabove, although the present disclosure is described by specific matters such as concrete components, and the like, exemplary embodiments, and drawings, they are provided only for assisting in the entire understanding of the present disclosure. Therefore, the present disclosure is not limited to the exemplary embodiments. Various modifications and changes may be made by those skilled in the art to which the present invention pertains without departing from the spirit and scope of the present disclosure. Therefore, the spirit of the present disclosure should not be limited to the above-described exemplary embodiments, and the following claims as well as all technical spirits modified equally or equivalently to the claims should be interpreted to fall within the scopes and spirits of the disclosure.

Claims

1. A method for predicting a collision with a target vehicle by a subject vehicle, comprising:

calculating, by a controller, a driving trajectory of the subject vehicle based on a yaw rate using driving information of the subject vehicle;

evaluating, by the controller, a driving trajectory of a the target vehicle for a predetermined period of time using driving information of the target vehicle including information from an imaging device mounted on the subject vehicle for obtaining a front image and information from a plurality of radar sensors mounted on the subject vehicle; and

predicting, by the controller, at least one collision type of a plurality of classified collision types by analyzing a collision possibility between the subject vehicle and the target vehicle based on the driving trajectory of the subject vehicle and the driving trajectory of the target vehicle, wherein

the predicting of the at least one collision type includes:

determining, by the controller, the at least one collision type based on a time difference between a time when a portion of the target vehicle intersects with a path of the driving trajectory of the subject vehicle (TTI) and a time when the target vehicle angularly-exits from a path of a circular trajectory of the subject vehicle based on a substantial center point of a curvature radius of the driving trajectory of the subject vehicle (TTAE) and a time difference between a time when the portion of the target vehicle angularly-intersects with the path of the circular trajectory of the subject vehicle based on the substantial center point of the curvature radius of the driving trajectory of the subject vehicle (TTAI) and a time when an entirety of the target vehicle exits from the path of the driving trajectory of the subject vehicle (TTE), and

the evaluating of the driving trajectory of the target vehicle includes:

analyzing, by the controller, the driving information of the target vehicle as the driving trajectory of the target vehicle;

estimating, by the controller, a velocity, an acceleration, and a yaw rate of the target vehicle using the driving information of the target vehicle; and

calculating, by the controller, the driving trajectory of the target vehicle based on the velocity, the acceleration, and the yaw rate of the target vehicle; and

calculating, by the controller, locations of the target vehicle at a predetermined time unit during the predetermined period of time based on the velocity, the acceleration, and the yaw rate of the target vehicle.

2. The method according to claim 1, wherein the method further includes predicting, by the controller, a the collision with the target vehicle in an omni-direction.

3. The method according, to claim 1, wherein the target vehicle includes at least one selected from the group consisting of: a front vehicle, a crossing vehicle, an oncoming vehicle, and a rear vehicle.

4. The method according to claim 1, wherein the predicting of the at least one collision type further includes:

calculating, by the controller, tracking information (TTX) which is related to a time in which the target vehicle intersects with or exits from the driving trajectory of the subject vehicle the TTI, the TTE, the TTAI, and the TTAE during the predetermined period of time; and

determining, by the controller, collision flags based on conditions that use the TTX one or more of the TTI, the TTE, the TTAI, and the TTAE.

5. The method according to claim 4, wherein the TTX predicting of the at least one collision type further includes:

the TTI;

the TTE;

the TTAI;

the TTAE;

calculating, by the controller, a time when the portion of the target vehicle intersects with the path of the driving trajectory of the subject vehicle while the subject vehicle decelerates (TTI_d); and

calculating, by the controller, a time when the target vehicle exits from the path of the driving trajectory of the subject vehicle while the subject vehicle accelerates (TTE_a).

6. The method according to claim 4, wherein the plurality of classified collision types includes at least two selected from a group consisting of:

a non-collision,

a first rear collision when the subject vehicle collides into a rear side of the target vehicle,

a collision between a front of the subject vehicle and a side rear of the target vehicle,

a collision between the front of the subject vehicle and a front of the target vehicle,

a collision between the front of the subject vehicle and a front of the target vehicle,

a collision between a side rear of the subject vehicle and the front of the target vehicle, and

a second rear collision when the target vehicle collides into a rear side of the subject vehicle.

7. An apparatus for predicting a collision with a target vehicle by a subject vehicle, comprising:

a memory configured to store program instructions; and

a controller configured to execute the program instructions, the program instructions when executed configured to:;

an imaging device mounted on the subject vehicle for obtaining a front image; and

a plurality of radar sensors mounted on the subject vehicle,

wherein, when the program instructions are executed, the controller is configured to:

calculate a driving trajectory of the subject vehicle based on a yaw rate using driving information of the subject vehicle using a subject vehicle path predicting unit;

evaluate a driving trajectory of a the target vehicle for a predetermined period of time using driving information of the target vehicle using a situation awareness unit, the driving information of the target vehicle including information from an the imaging device mounted on the subject vehicle for obtaining a front image and information from a the plurality of radar sensors mounted on the subject vehicle; and

predict at least one collision type of a plurality of classified collision types by analyzing a collision possibility between the subject vehicle and the target vehicle based on the driving trajectory of the subject vehicle and the driving trajectory of the target vehicle, wherein

when evaluating the driving trajectory of the target vehicle, the controller is configured to:

analyze the driving information of the target vehicle using a target path predicting unit;

estimate a velocity, an acceleration, and a yaw rate of the target vehicle using the target path predicting unit driving information of the target vehicle;

calculate the driving trajectory of the target vehicle based on the velocity, the acceleration, and the yaw rate of the target vehicle; and

calculate locations of the target vehicle at a predetermined time unit during the predetermined period of time based on the velocity, the acceleration, and the yaw rate of the target vehicle using the target patch predicting unit;, and

predict at least one collision type of a plurality of classified collision types by analyzing a collision possibility between the subject vehicle and the target vehicle using the situation awareness unit; and

when predicting the at least one collision type, the controller is configured to:

determine the at least one collision type based on a time difference between a time when a portion of the target vehicle intersects with a path of the driving trajectory of the subject vehicle (TTI) and a time when the target vehicle angularly-exits from a path of a circular trajectory of the subject vehicle based on a substantial center point of a curvature radius of the driving trajectory of the subject vehicle (TTAE) and a time difference between a time when the portion of the target vehicle angularly-intersects with the path of the circular trajectory of the subject vehicle based on the substantial center point of the curvature radius of the driving trajectory of the subject vehicle (TTAI) and a time when an entirety of the target vehicle exits from the path of the driving trajectory of the subject vehicle (TTE) using a collision determining unit.

8. The apparatus according to claim 7, wherein the controller is further configured to predict the collision emergency with the target vehicle in an omni-direction.

9. The apparatus according to claim 7, wherein the target vehicle includes at least one selected from the group consisting of: a front vehicle, a crossing vehicle, an oncoming vehicle, or and a rear vehicle.

10. The apparatus according to claim 7, wherein the controller is further configured to:

calculate tracking information (TTX), which is related to a time in which the target vehicle intersects with or exits from the driving trajectory of the subject vehicle the TTI, the TTE, the TTAI, and the TTAE during the predetermined period of time, using a tracking information calculating unit; and

determine collision flags based on conditions that use the TTX, using the collision determining unit one or more of the TTI, the TTE, the TTAI, and the TTAE.

11. The apparatus according to claim 10, wherein the TTX includes controller is further configured to:

the TTI;

the TTE;

the TTAI;

the TTAE;

calculate a time when the portion of the target vehicle intersects with the path of the driving trajectory of the subject vehicle while the subject vehicle decelerates (TTI_d); and

calculate a time when the target vehicle exits from the path of the driving trajectory of the subject vehicle while the subject vehicle accelerates (TTE_a).

12. The apparatus according to claim 10, wherein the plurality of classified collision types include at least two selected from a group consisting of:

a non-collision,

a first rear collision when the subject vehicle collides into a rear side of the target vehicle,

a collision between a front of the subject vehicle and a side rear of the target vehicle,

a collision between the front of the subject vehicle and a front of the target vehicle,

a collision between the front of the subject vehicle and a front of the target vehicle,

a collision between a side rear of the subject vehicle and the front of the target vehicle, and

a second rear collision when the target vehicle collides into a rear side of the subject vehicle.

13. A non-transitory computer readable medium containing program instructions executed by a processor for predicting a collision with a target vehicle by a subject vehicle, the computer readable medium comprising:

program instructions that calculate a driving trajectory of the subject vehicle based on a yaw rate using driving information of the subject vehicle;

program instructions that evaluate a driving trajectory of a the target vehicle for a predetermined period of time using driving information of the target vehicle including information from an imaging device mounted on the subject vehicle for obtaining a front image and information from a plurality of radar sensors mounted on the subject vehicle; and

program instructions that predict at least one collision type of a plurality of classified collision types by analyzing a collision possibility between the subject vehicle and the target vehicle based on the driving trajectory of the subject vehicle and the driving trajectory of the target vehicle, wherein

the program instructions that evaluate the driving trajectory of the target vehicle include:

program instructions that analyze the driving information of the target vehicle as the driving trajectory of the target vehicle;

program instructions that estimate a velocity, an acceleration, and a yaw rate of the target vehicle using the driving information of the target vehicle;

program instructions that calculate the driving trajectory of the target vehicle based on the velocity, the acceleration, and the yaw rate of the target vehicle; and

program instructions that calculate locations of the target vehicle at a predetermined time unit during the predetermined period of time based on the velocity, the acceleration, and the yaw rate of the target vehicle;, and

program instructions that predict at least one collision type of a plurality of classified collision types by analyzing a collision possibility between the subject vehicle and the target vehicle based on the driving trajectory of the subject vehicle and the driving trajectory of the target vehicle; and

the program instructions that predict at least one collision type include:

program instructions that determine the at least one collision type based on a time difference between a time when a portion of the target vehicle intersects with a path of the driving trajectory of the subject vehicle (TTI) and a time when the target vehicle angularly-exits from a path of a circular trajectory of the subject vehicle based on a substantial center point of a curvature radius of the driving trajectory of the subject vehicle (TTAE) and a time difference between a time when the portion of the target vehicle angularly-intersects with the path of the circular trajectory of the subject vehicle based on the substantial center point of the curvature radius of the driving trajectory of the subject vehicle (TTAI) and a time when an entirety of the target vehicle exits from the path of the driving trajectory of the subject vehicle (TTE).

14. The non-transitory computer readable medium of claim 13, further comprising:

program instructions that calculate tracking information (TTX), which is related to a time in which the target vehicle intersects with or exits from the driving trajectory of the subject vehicle the TTI, the TTE, the TTAI, and the TTAE during the predetermined period of time; and

program instructions that determine collision flags based on conditions that use the TTX one or more of the TTI, the TTE, the TTAI, and the TTAE.

15. A method for predicting a collision with a target vehicle by a subject vehicle, comprising:

calculating, by a controller, a driving trajectory of the subject vehicle based on a velocity of the subject vehicle;

evaluating, by the controller, a driving trajectory of the target vehicle for a predetermined period of time using driving information of the target vehicle including information from an imaging device mounted on the subject vehicle for obtaining a front image and information from a plurality of radar sensors mounted on the subject vehicle;

predicting, by the controller, at least one collision type of a plurality of classified collision types by analyzing a collision possibility between the subject vehicle and the target vehicle based on the driving trajectory of the subject vehicle and the driving trajectory of the target vehicle; and

when the collision between the subject vehicle and the target vehicle is predicted to occur, calculating, by the controller, a timing-to-collision based on the velocity of the subject vehicle and the driving information of the target vehicle,

wherein the evaluating of the driving trajectory of the target vehicle includes:

estimating, by the controller, a velocity, an acceleration, and a yaw rate of the target vehicle using the driving information of the target vehicle;

calculating, by the controller, the driving trajectory of the target vehicle based on the velocity, the acceleration, and the yaw rate of the target vehicle; and

calculating, by the controller, locations of the target vehicle during the predetermined period of time based on the velocity, the acceleration, and the yaw rate of the target vehicle, and

wherein the predicting of the at least one collision type includes:

determining, by the controller, the at least one collision type based on a time difference between a time when a portion of the target vehicle intersects with a path of the driving trajectory of the subject vehicle (TTI) and a time when the target vehicle angularly-exits from a path of a circular trajectory of the subject vehicle based on a substantial center point of a curvature radius of the driving trajectory of the subject vehicle (TTAE) and a time difference between a time when the portion of the target vehicle angularly-intersects with the path of the circular trajectory of the subject vehicle based on the substantial center point of the curvature radius of the driving trajectory of the subject vehicle (TTAI) and a time when an entirety of the target vehicle exits from the path of the driving trajectory of the subject vehicle (TTE).

16. The method according to claim 15, wherein the target vehicle includes at least one selected from the group consisting of: a front vehicle, a crossing vehicle, an oncoming vehicle, and a rear vehicle.

17. The method according to claim 15, wherein the predicting of the at least one collision type further includes:

calculating, by the controller, the TTI, the TTE, the TTAI, and the TTAE during the predetermined period of time; and

determining, by the controller, collision flags based on conditions that use one or more of the TTI, the TTE, the TTAI, and the TTAE.

18. The method according to claim 17, wherein the predicting of the at least one collision type further includes:

calculating, by the controller, a time when the portion of the target vehicle intersects with the path of the driving trajectory of the subject vehicle while the subject vehicle decelerates (TTI_d); and

calculating, by the controller, a time when the target vehicle exits from the path of the driving trajectory of the subject vehicle while the subject vehicle accelerates (TTE_a).

19. The method according to claim 18, wherein the plurality of classified collision types includes at least two selected from a group consisting of:

a non-collision,

a first rear collision when the subject vehicle collides into a rear side of the target vehicle,

a collision between a front of the subject vehicle and a side rear of the target vehicle,

a collision between the front of the subject vehicle and a front of the target vehicle,

a collision between a side rear of the subject vehicle and the front of the target vehicle, and

a second rear collision when the target vehicle collides into a rear side of the subject vehicle.

20. An apparatus for predicting a collision with a target vehicle by a subject vehicle, comprising:

a memory configured to store program instructions;

a controller configured to execute the program instructions;

an imaging device mounted on the subject vehicle for obtaining a front image; and

a plurality of radar sensors mounted on the subject vehicle,

wherein, when the program instructions are executed, the controller is configured to:

calculate a driving trajectory of the subject vehicle based on a velocity of the subject vehicle;

evaluate a driving trajectory of the target vehicle for a predetermined period of time using driving information of the target vehicle including information from the imaging device and information from the plurality of radar sensors;

predict at least one collision type of a plurality of classified collision types by analyzing a collision possibility between the subject vehicle and the target vehicle; and

when the collision between the subject vehicle and the target vehicle is predicted to occur, calculate a timing-to-collision based on the velocity of the subject vehicle and the driving information of the target vehicle,

wherein, when evaluating the driving trajectory of the target vehicle, the controller is configured to:

estimate a velocity, an acceleration, and a yaw rate of the target vehicle using the driving information of the target vehicle;

calculate the driving trajectory of the target vehicle based on the velocity, the acceleration, and the yaw rate of the target vehicle; and

calculate locations of the target vehicle during the predetermined period of time based on the velocity, the acceleration, and the yaw rate of the target vehicle, and

wherein, when predicting the at least one collision type, the controller is configured to:

determine the at least one collision type based on a time difference between a time when a portion of the target vehicle intersects with a path of the driving trajectory of the subject vehicle (TTI) and a time when the target vehicle angularly-exits from a path of a circular trajectory of the subject vehicle based on a substantial center point of a curvature radius of the driving trajectory of the subject vehicle (TTAE) and a time difference between a time when the portion of the target vehicle angularly-intersects with the path of the circular trajectory of the subject vehicle based on the substantial center point of the curvature radius of the driving trajectory of the subject vehicle (TTAI) and a time when an entirety of the target vehicle exits from the path of the driving trajectory of the subject vehicle (TTE).

21. The apparatus according to claim 20, wherein the controller is further configured to predict the collision with the target vehicle in an omni-direction.

22. The apparatus according to claim 20, wherein the target vehicle includes at least one selected from the group consisting of: a front vehicle, a crossing vehicle, an oncoming vehicle, and a rear vehicle.

23. The apparatus according to claim 20, wherein the controller is further configured to:

calculate the TTI, the TTE, the TTAI, and the TTAE during the predetermined period of time; and

determine collision flags based on conditions that use one or more of the TTI, the TTE, the TTAI, and the TTAE.

24. The apparatus according to claim 23, wherein the controller is further configured to:

calculate a time when the portion of the target vehicle intersects with the path of the driving trajectory of the subject vehicle while the subject vehicle decelerates (TTI_d); and

calculate a time when the target vehicle exits from the path of the driving trajectory of the subject vehicle while the subject vehicle accelerates (TTE_a).

25. The apparatus according to claim 24, wherein the plurality of classified collision types include at least two selected from a group consisting of:

a non-collision,

a first rear collision when the subject vehicle collides into a rear side of the target vehicle,

a collision between a front of the subject vehicle and a side rear of the target vehicle,

a collision between the front of the subject vehicle and a front of the target vehicle,

a collision between a side rear of the subject vehicle and the front of the target vehicle, and

a second rear collision when the target vehicle collides into a rear side of the subject vehicle.