KR20220161725A - Forward collision avoidance system and method for vehicle - Google Patents

Abstract

The present invention relates to a front collision prevention system of a vehicle and a front collision prevention method. The vehicle front collision prevention system may comprise: a driving pattern learning unit which determines and learns a driver's driving pattern and generates learning information; and a control unit which calculates a collision prediction time based on distance information from an object and image information obtained from surroundings of the vehicle, and sets a deceleration time point and a warning notification time point based on the collision prediction time and the learning information. Provided is the front collision prevention system of the vehicle, capable of varying the warning notification time point and the deceleration time point of the front collision prevention system.

Description

Forward collision avoidance system and front collision avoidance method of vehicle {FORWARD COLLISION AVOIDANCE SYSTEM AND METHOD FOR VEHICLE}

The present invention relates to a system and method for preventing frontal collision of a vehicle.

In general, a vehicle refers to a device that transports people or cargo from one place to another by driving wheels. For example, a two-wheeled vehicle such as a motorcycle, a four-wheeled vehicle such as a sedan, and a train also belong to vehicles.

In recent years, in order to increase the safety and convenience of users using vehicles, the development of technologies for incorporating various sensors and electronic devices into vehicles is accelerating.

Among devices and systems developed to increase driver's safety and convenience by incorporating various sensors and electronic devices into vehicles, there is a forward collision avoidance system.

The forward collision avoidance system provides a warning to the driver when an object predicted to collide is detected in front of the vehicle, and performs a role of decelerating the vehicle or braking the vehicle.

Since the warning notification time and deceleration or braking time of the existing front collision avoidance system are applied according to the speed of the host vehicle, a warning notification is provided and the vehicle can be decelerated in a situation where the driver feels safe. Warning notifications may not be provided or vehicle deceleration may not be performed in situations that feel unsafe.

Therefore, since the driver's satisfaction with the existing front collision avoidance system may be low, improvement of the front collision avoidance system is urgently needed.

An embodiment of the present invention is to provide a front collision avoidance system for a vehicle capable of changing a warning notification time and deceleration time of a forward collision avoidance system by learning a driver's driving pattern.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

A forward collision avoidance system of a vehicle according to an embodiment of the present invention is based on a driving pattern learning unit that determines and learns a driver's driving pattern to generate learning information, and distance information to an object and image information obtained from the surroundings of the vehicle. A control unit for calculating a collision prediction time and setting a deceleration time point and a warning notification time point based on the collision prediction time and the learning information may be included.

In an embodiment, the driving pattern learner may generate the learning information by determining and learning the driver's driving pattern based on an acceleration, an accelerator pedal amount, a deceleration pedal amount, and the distance information.

In an embodiment, the driving pattern learning unit may determine and learn the driver's driving pattern, select one of a plurality of driving patterns, and generate a weight for the selected driving pattern as the learning information.

In one embodiment, the control unit determines whether to determine deceleration and whether to notify a warning based on the predicted collision time, and provides deceleration information to a braking device at the time of deceleration according to the learning information when it is determined that deceleration is necessary. And, if it is determined that the warning notification is necessary, the notification information may be provided to the notification unit at the time of the warning notification according to the learning information.

In one embodiment, the driver driving pattern includes first to third driver driving patterns, the learning information includes a weight for each of the first to third driver driving patterns, and the driving pattern learning unit comprises: One of the first to third driver driving patterns may be selected based on the acceleration, the accelerator pedal amount, the deceleration pedal amount, and the distance information, and the learning information including a weight for the selected driver driving pattern may be generated. .

In one embodiment, a weight for the first driver driving pattern among the first to third driver driving patterns is the largest and a weight for the third driver driving pattern is the smallest, and the control unit determines the collision prediction If it is determined that deceleration is necessary based on time, the deceleration time point is determined according to the value of the weight included in the learning information, and if it is determined that a warning notification is required based on the collision prediction time, the weight value included in the learning information The warning notification time may be determined according to the value.

In one embodiment, the control unit sets the deceleration time and the warning notification time according to the learning information including the weight of the first driver's driving pattern to the deceleration time and the warning notification according to the weight of another driver's driving pattern. may be delayed beyond the time point.

In one embodiment, the control unit sets the deceleration time and the warning notification time according to the learning information including the weight of the third driver's driving pattern to the deceleration time and the warning notification according to the weight of another driver's driving pattern. It can be advanced ahead of time.

In another embodiment of the present invention, a method for preventing a frontal collision of a vehicle includes determining and learning a driver's driving pattern based on an acceleration, an accelerator pedal amount, a brake pedal amount, and a distance to an object, and a weighted value according to the learning result. Calculating the expected collision time based on the distance to the object and images obtained from the surroundings of the vehicle, determining whether to decelerate and whether to notify a warning based on the estimated collision time, and When it is determined or a warning notification is determined, setting a deceleration time point and a warning notification time point according to the weight may be included.

In another embodiment, the driver driving pattern includes a plurality of driver driving patterns, and the determining and learning of the driver driving pattern includes the acceleration, the amount of the accelerator pedal, the amount of the brake pedal, and the object. One of the plurality of driver driving patterns may be selected based on the distance.

In another embodiment, the calculating of the weight may include calculating a weight for the selected driver driving pattern when one of the plurality of driver driving patterns is selected.

In another embodiment, in the step of varying the deceleration time and the warning notification time, the deceleration time and the warning notification time may be advanced or delayed according to a weight value according to the selected driver driving pattern.

In another embodiment, the step of varying the deceleration time and the warning notification time may include delaying the deceleration time and the warning notification as the value of the weight increases, and the deceleration time and the warning as the value of the weight decreases. timing can be advanced.

The present technology has the advantage of improving the driver's satisfaction with the front collision avoidance system by learning the driver's driving pattern and changing the warning notification time and deceleration time to match the driver's driving pattern.

In addition to this, various effects identified directly or indirectly through this document may be provided.

1 is a diagram showing the configuration of a front collision avoidance system for a vehicle according to an embodiment of the present invention.
2 is a diagram showing the configuration of a control unit constituting a front collision avoidance system for a vehicle according to an embodiment of the present invention.
3 is a flowchart illustrating learning of a driver's driving pattern of a system for preventing a vehicle from colliding with a vehicle according to an embodiment of the present invention.

Hereinafter, some embodiments of the present invention will be described in detail through exemplary drawings. In adding reference numerals to components of each drawing, it should be noted that the same components have the same numerals as much as possible even if they are displayed on different drawings. In addition, in describing an embodiment of the present invention, if it is determined that a detailed description of a related known configuration or function hinders understanding of the embodiment of the present invention, the detailed description will be omitted.

In describing the components of the embodiment of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are only used to distinguish the component from other components, and the nature, order, or order of the corresponding component is not limited by the term. In addition, unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

Hereinafter, embodiments of the present invention will be described in detail with reference to FIGS. 1 to 3 .

1 is a diagram showing the configuration of a front collision avoidance system for a vehicle according to an embodiment of the present invention.

Referring to FIG. 1 , the control unit 10 according to an embodiment of the present invention may be implemented inside a vehicle. At this time, the control unit 10 may be integrally formed with the internal control units of the vehicle, or may be implemented as a separate device and connected to the control units of the vehicle by a separate connection means.

Referring to FIG. 1 , a front collision avoidance system for a vehicle according to an embodiment of the present invention includes a distance sensor 10, an image sensor 20, a driving pattern learning unit 30, a controller 40, and a braking device 50. ) and a notification unit 60.

The distance sensor 10 may measure a distance between an object around the vehicle and the vehicle, and provide the measured result to the control unit 40 as distance information.

For example, the distance sensor 10 may include a radar.

The image sensor 20 may acquire an image around the vehicle and provide the obtained image to the control unit 40 as image information.

For example, the image sensor 20 may include a camera.

The driving pattern learning unit 30 may learn the driver's driving pattern and provide the learning result to the controller 40 .

For example, the driving pattern learner 30 recognizes and learns a driver's driving pattern based on acceleration, an accelerator pedal amount, a braking pedal amount, and a distance to an object, and provides the learning result to the control unit 40 as learning information. can

In this case, the driver's driving pattern may include an acceleration time, deceleration time, acceleration amount, and deceleration amount by the driver according to a distance from a vehicle in front.

More specifically, by way of example, the driving pattern learner 30 determines that the driver accelerates and decelerates more quickly than a typical driver and maintains a shorter distance from the vehicle in front than a typical driver. By recognizing and learning as a pattern, the learning result can be provided as learning information.

When the driving pattern learner 30 determines that the driver's rapid acceleration, rapid deceleration, and distance to the vehicle in front are within the general driver's range, the driving pattern learning unit 30 recognizes and learns the second driver's driving pattern, and provides the learning result as learning information. can do.

The driving pattern learner 30 recognizes and learns as a third driver driving pattern when it is determined that the driver's rapid acceleration and deceleration are less than that of a general driver and that the driver maintains a longer distance from the vehicle in front than a general driver, and learns the learning result can be provided as learning information.

The control unit 40 generates deceleration information and notification information based on distance information from the distance sensor 10, image information from the image sensor 20, and learning information from the driving pattern learning unit 30, and generates Deceleration information may be provided to the braking device 50 and generated notification information may be provided to the notification unit 60 .

For example, the controller 40 may select a collision prediction object in front of the vehicle based on the distance information and image information, and calculate a collision prediction time with the selected collision prediction object.

In addition, the control unit 40 may determine whether to decelerate and whether to notify a warning based on the calculated collision prediction time.

Also, if it is determined that deceleration is necessary, the control unit 40 may set a deceleration time point based on learning information.

In addition, the control unit 40 may set a deceleration time point based on the learning information when it is determined that a warning notification is necessary.

As a result, the controller 40 may delay or speed up the warning notification time and deceleration time according to the recognized driver's driving pattern.

The braking device 50 may decelerate or brake the vehicle based on the deceleration information.

In this case, the deceleration information includes a deceleration time point, and the braking device 50 may include an automatic emergency braking (AEB) device.

The notification unit 60 may provide a warning notification as visual information and auditory information to the driver based on the notification information.

At this time, the notification information includes a warning notification time point, and the notification unit 60 may include a cluster.

2 is a diagram showing the configuration of a control unit constituting a front collision avoidance system for a vehicle according to an embodiment of the present invention.

Referring to FIG. 2, the control unit 40 includes a collision prediction object selection unit 41, a collision prediction time calculation unit 42, a deceleration determination unit 43, a warning notification determination unit 44, and a deceleration information output unit 45. and a notification information output unit 46 .

The collision prediction object selection unit 41 may select a collision prediction object based on distance information and image information.

For example, the collision prediction object selection unit 41 may select an object existing in the driving direction of the vehicle among objects existing around the vehicle as a collision prediction object by combining distance information and image information.

The collision prediction time calculation unit 42 may calculate a collision prediction time with a collision prediction object based on the selected collision prediction object and distance information.

In this case, the collision prediction time may include Time to Collision (TTC).

The deceleration determination unit 43 may determine whether to decelerate based on the predicted collision time.

For example, the deceleration determination unit 43 may determine that the vehicle needs to decelerate when the collision prediction time decreases to less than the first preset time.

The warning notification determining unit 44 may determine whether or not to notify a warning based on the predicted collision time.

For example, when the collision prediction time decreases to less than the second preset time, it may be determined that a warning notification is required for the driver.

In this case, the first preset time may be shorter than the second preset time.

When the deceleration determination unit 43 determines that deceleration is necessary, the deceleration information output unit 45 may vary the output timing of the deceleration information provided to the braking device according to learning information.

For example, if it is determined that deceleration is necessary, the deceleration information output unit 45 may advance or delay the output timing of the deceleration information according to a weight according to learning information.

For example, in more detail, the operation of the deceleration information output unit 45 will be described as follows.

At this time, the learning information recognized as the first driver driving pattern may include a weight of 1.2, the learning information recognized as the second driver driving pattern may include a weight of 1, and the learning information recognized as the third driver driving pattern may include a weight of 1. It is assumed that learning information includes a weight of 0.8.

When the deceleration information output unit 45 receives the learning information (weight = 1) recognized as the second driver's driving pattern, the deceleration determination unit 43 determines that deceleration is necessary. When the delay time elapses, deceleration information may be provided to the braking device 50 .

When the deceleration information output unit 45 receives the learning information (weight = 1,2) recognized as the first driver's driving pattern, the deceleration determination unit 43 sets a weight (= 1.2) from the point at which it is determined that deceleration is necessary. When the delay time for lapses, deceleration information may be provided to the braking device 50 .

When the deceleration information output unit 45 receives the learning information (weight = 0.8) recognized as the third driver's driving pattern, the deceleration determination unit 43 determines that deceleration is necessary for the weight (= 0.8). When the delay time elapses, deceleration information may be provided to the braking device 50 .

That is, the front collision avoidance system of a vehicle according to an embodiment of the present invention learns the driver's driving pattern, determines which driving pattern the driver is driving, and changes the deceleration time point according to the weighted value according to the determined driving pattern. .

As described above, in the front collision avoidance system of a vehicle according to an embodiment of the present invention, the deceleration time point may be delayed in the first driver driving pattern compared to the case determined in the second driver driving pattern, and the second driver driving pattern In the case of the third driver's driving pattern, the deceleration time point may be advanced compared to the case where it is determined as .

The notification information output unit 46 may change the output timing of the notification information provided to the braking device according to the learning information when the warning notification determination unit 43 determines that deceleration is necessary.

For example, when it is determined that warning notification is necessary, the notification information output unit 46 may advance or delay the output timing of notification information according to a weight according to learning information.

For example, in more detail, the operation of the notification information output unit 46 will be described as follows.

At this time, the learning information recognized as the first driver driving pattern may include a weight of 1.2, the learning information recognized as the second driver driving pattern may include a weight of 1, and the learning information recognized as the third driver driving pattern may include a weight of 1. It is assumed that learning information includes a weight of 0.8.

When the notification information output unit 46 receives the learning information (weight = 1) recognized as the second driver's driving pattern, the warning notification determination unit 44 determines that the warning notification is necessary. When the delay time for has elapsed, notification information may be provided to the notification unit 60 .

When the notification information output unit 46 receives the learning information (weight = 1, 2) recognized as the first driver's driving pattern, the warning notification determination unit 44 determines that the warning notification is necessary, and sets the weight value (= When the delay time for 1.2) elapses, notification information may be provided to the notification unit 60 .

When the notification information output unit 46 receives the learning information (weight = 0.8) recognized as the third driver's driving pattern, the warning notification determination unit 44 sets a weight value (= 0.8) from the point at which the warning notification is determined to be necessary. When the delay time for has elapsed, notification information may be provided to the notification unit 60 .

That is, the front collision avoidance system of a vehicle according to an embodiment of the present invention learns the driver's driving pattern, determines which driving pattern the driver is driving, and changes the notification time according to the weight according to the determined driving pattern. .

As described above, in the front collision avoidance system of a vehicle according to an embodiment of the present invention, the notification time may be delayed in the case of the first driver driving pattern rather than the case in which the second driver driving pattern is determined, and the second driver driving pattern In the case of the third driver's driving pattern, the notification time may be advanced compared to the case where it is determined as .

3 is a flowchart illustrating learning of a driver's driving pattern of a system for preventing a vehicle from colliding with a vehicle according to an embodiment of the present invention.

As shown in FIG. 3, the front collision prevention system of a vehicle according to an embodiment of the present invention learns a driver's driving pattern by classifying it into low-speed driving and high-speed driving, and changes the warning notification time using the learned result. can

Referring to FIG. 3 , a method for learning a driver's driving pattern of a system for preventing a frontal collision of a vehicle according to an embodiment of the present invention includes a step of storing vehicle information (S1), a step of determining and learning a driver's driving pattern (S2), and a low-speed collision warning time point. Calculation step (S3), deceleration time calculation step (S4), high-speed road driving determination step (S5), high-speed collision warning time calculation step (S6), collision warning time update step (S7) and deceleration time update step (S8) can include

The step of storing vehicle information ( S1 ) may include receiving and storing information for determining a driver's driving pattern. At this time, the information for determining the driver's driving pattern may include information on acceleration, accelerator pedal amount, brake pedal amount, and distance to the other vehicle.

The driver driving pattern determination and learning step ( S2 ) may include determining and learning the driver driving pattern with the information stored in the vehicle information storage step ( S1 ).

Calculating the low-speed collision warning time point (S3) may include calculating a weight for the first warning time point according to the driver driving pattern learned in the driver driving pattern determination and learning step (S2).

The step of calculating the deceleration time (S4) may include calculating a weight for the deceleration time according to the driver driving pattern learned in the driver driving pattern determination and learning step (S2).

The highway driving determination step ( S5 ) may include determining whether the driving road of the vehicle is a general road or an expressway according to the location information of the navigation system.

If it is determined that the high-speed road driving is determined in the high-speed road driving determination step S5, the high-speed collision warning time calculation step S6 may be performed.

On the other hand, if it is determined in the high-speed road driving step (S5) that it is a general road driving step, the collision warning time update step (S7) may be performed.

The calculation of the high-speed collision warning time point (S6) may include calculating a weight for the second warning time point according to the driver driving pattern learned in the driver driving pattern determination and learning step (S2).

The collision warning time update step (S7) may include determining the warning time based on the weight calculated in the low-speed collision warning time calculation step (S3) and the weight calculated in the high-speed collision warning time calculation step (S4). .

The step of updating the deceleration time (S8) may include determining the deceleration time based on the weight calculated in the step of calculating the deceleration time (S4).

As described above, the system for preventing a front collision of a vehicle according to an embodiment of the present invention may separately provide a point in time for providing a collision warning notification to a driver on a general road and a highway.

As a result, the front collision avoidance system of a vehicle according to an embodiment of the present invention determines and learns the driver's driving pattern to notify a collision warning and change the deceleration time, thereby improving the driver's satisfaction with the front collision avoidance system. can make it

The above description is merely an example of the technical idea of the present invention, and various modifications and variations can be made to those skilled in the art without departing from the essential characteristics of the present invention.

Therefore, the embodiments disclosed in the present invention are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments. The protection scope of the present invention should be construed according to the following claims, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

Claims (13)

a driving pattern learning unit that determines and learns a driver's driving pattern and generates learning information; and
a control unit that calculates a collision prediction time based on distance information from an object and image information obtained from the surroundings of the vehicle, and sets a deceleration time point and a warning notification time point based on the collision prediction time and the learning information;
Front collision avoidance system of a vehicle comprising a.
The method of claim 1,
The driving pattern learning unit,
The forward collision avoidance system of a vehicle, characterized in that the learning information is generated by determining and learning the driver's driving pattern based on the acceleration, the amount of the accelerator pedal, the amount of the deceleration pedal, and the distance information.
The method of claim 1,
The driving pattern learning unit,
The forward collision avoidance system of a vehicle, characterized in that by determining and learning the driver's driving pattern, selecting one of a plurality of driving patterns, and generating a weight for the selected driving pattern as the learning information.
The method of claim 1,
The control unit,
Based on the collision prediction time, it is determined whether to determine deceleration and whether to notify a warning,
When it is determined that deceleration is necessary, deceleration information is provided to the brake device at the time of deceleration according to the learning information;
and providing notification information to a notification unit at the time of the warning notification according to the learning information when it is determined that a warning notification is necessary.
The method of claim 1,
The driver driving pattern includes first to third driver driving patterns,
The learning information includes weights for each of the first to third driver driving patterns,
The driving pattern learning unit,
Selecting one of the first to third driver driving patterns based on an acceleration, an accelerator pedal amount, a deceleration pedal amount, and the distance information, and generating the learning information including a weight for the selected driver driving pattern. vehicle's forward collision avoidance system.
The method of claim 5,
Among the first to third driver driving patterns, the weight for the first driver driving pattern is the largest and the weight for the third driver driving pattern is the smallest;
The control unit,
If it is determined that deceleration is necessary based on the collision prediction time, the deceleration time point is determined according to a value of a weight included in the learning information;
If it is determined that a warning notification is necessary based on the collision prediction time, the warning notification time point is determined according to a weight value included in the learning information.
The method of claim 6,
The control unit,
The deceleration time and the warning notification time according to the learning information including the weight of the first driver's driving pattern are delayed than the deceleration time and the warning notification time according to the weight of another driver's driving pattern. anti-collision system.
The method of claim 7,
The control unit,
The deceleration time and the warning notification time according to the learning information including the weight of the third driver's driving pattern are advanced than the deceleration time and the warning notification time according to the weight of another driver's driving pattern. Forward collision avoidance system.
determining and learning a driver's driving pattern based on an acceleration, an accelerator pedal amount, a brake pedal amount, and a distance to an object;
Calculating a weight according to the learning result;
Calculating an estimated collision time based on a distance to the object and an image obtained from the surroundings of the vehicle;
Determining whether to decelerate and whether to notify a warning based on the predicted collision time; and
setting a deceleration time point and a warning notification time point according to the weight when it is determined that deceleration is necessary or a warning notification is determined;
A method for preventing a frontal collision of a vehicle, comprising:
The method of claim 9,
The driver driving pattern includes a plurality of driver driving patterns,
The step of determining and learning the driver's driving pattern,
and selecting one of the plurality of driver driving patterns based on the acceleration, the amount of the accelerator pedal, the amount of the brake pedal, and the distance to the object.
The method of claim 10,
In the step of calculating the weight,
and calculating a weight for the selected driver driving pattern when one of the plurality of driver driving patterns is selected.
The method of claim 11,
The step of varying the deceleration time and the warning notification time,
The forward collision avoidance method of a vehicle, characterized in that advancing or delaying the deceleration time and the warning notification time according to the value of the weight according to the selected driver's driving pattern.
The method of claim 12,
The step of varying the deceleration time and the warning notification time,
The method of preventing collision of a vehicle, characterized in that the deceleration time and the warning notification are delayed as the value of the weight increases, and the deceleration time and the warning time are advanced as the value of the weight decreases.

Images