KR20220063846A - Autonomous driving system of vehicle and control method thereof - Google Patents

Abstract

The present invention comprises: a camera provided to capture a front image of a vehicle; a construction notification means notifying that a construction zone is positioned on a front side of the vehicle; a front vehicle tracking unit monitoring a construction zone passing situation of a front vehicle captured by the camera; a path setting unit setting a predicted lane and a target driving path by analyzing a construction zone driving path of the front vehicle tracked by the front vehicle tracking unit; and a control unit receiving information that the construction zone is positioned on the front side of the vehicle from the construction notification means, controlling the front vehicle tracking unit and the path setting unit, and allowing the vehicle to drive along the target driving path.

Description

Autonomous driving system of vehicle and its control method

The present invention relates to a technology for an autonomous driving system for a vehicle and a control method thereof, and more particularly, to a technology for driving a vehicle in a construction section of a road.

Autonomous driving vehicles, as much as possible, without driver intervention, detect surrounding and road conditions on their own, set an appropriate driving route accordingly, and aim to drive automatically along the set route. For this, autonomous driving can be implemented relatively easily.

However, if there is an area under construction in some sections of the road, due to the nature of the construction area, there is a limit to the recognition of the surroundings by the radar sensor provided in the vehicle due to the diffuse reflection of various facilities, equipment, materials, etc. Since it is not accurate and is not in a certain shape, there is a high possibility of an accident due to a malfunction of the autonomous driving system.

The matters described as the background technology of the present invention are only for enhancing the understanding of the background of the present invention, and should not be taken as acknowledging that they correspond to the prior art already known to those of ordinary skill in the art. will be

KR 102150138394 A

The present invention effectively sets the driving path that the vehicle must travel in order to safely pass the construction section in spite of various irregular circumstances when the vehicle runs on the construction section of the road, so that it can be driven accordingly, An object of the present invention is to provide an autonomous driving system for a vehicle and a control method therefor so that the reliability and safety of the vehicle can be greatly improved by reducing the possibility of a malfunction.

An autonomous driving system for a vehicle of the present invention for achieving the above object,

a camera provided to take an image of the front of the vehicle;

Construction notification means for notifying that the construction section is located in front of the vehicle;

a front vehicle tracking unit for monitoring the passing situation of the front vehicle photographed with the camera;

a route setting unit that analyzes the travel route of the construction section of the front vehicle tracked by the front vehicle tracking unit to set an expected lane and a target travel route;

a control unit receiving information that a construction section is located from the construction notification means, controlling the front vehicle tracking unit and the path setting unit, and driving the vehicle along the target driving path;

It is characterized in that it comprises a.

The construction notification means may be configured to recognize a construction sign from the front image taken with the camera and notify the control unit that the construction section is located.

The construction notification means may be configured to recognize the construction sign by deep learning from the front image taken with the camera.

The construction notification means may be configured as a notification switch for the driver to confirm that the construction section is located in front and turn on.

The construction notification means may be configured to notify the occupant of the vehicle that the construction section is located in front of the vehicle.

The front vehicle tracking unit tracks the position of the front vehicle among the front images captured by the camera, and when the front vehicle is about to deviate from the front image, the moving direction of the front vehicle being tracked within the range where the driving path of the vehicle can be checked It may be configured to rotate the camera along

the front vehicle tracking unit is configured to track the position of the front vehicle among the front images captured by the camera, and to provide information on this to the control unit when the front vehicle is about to deviate from the front image;

The control unit may be configured to rotate the camera according to the moving direction of the front vehicle being tracked within a range in which the driving path of the vehicle can be checked according to the information from the front vehicle tracking unit.

The route setting unit may be configured to set the expected lane and the target travel route by combining the map information on the road currently being driven with the travel route of the construction section of the front vehicle.

The route setting unit may be configured to set the expected lane and target driving route by using big data-based deep learning.

In addition, the method for controlling the autonomous driving system of the vehicle of the present invention for achieving the above object,

photographing a front image of the vehicle with a camera;

Recognizing that the construction section is located in front of the vehicle;

monitoring the condition of passing the construction section of the front vehicle photographed with the camera;

setting an expected lane and a target driving path by analyzing the driving path in the construction section of the monitored vehicle in front;

driving the vehicle along the target driving path;

It is characterized in that it comprises a.

In the step of recognizing that the construction section is located, by recognizing a construction sign from the front image taken with the camera, it is possible to recognize that the construction section is located in front of the vehicle.

In the step of recognizing that the construction section is located, it is possible to recognize the construction sign by deep learning from the front image taken with the camera.

In the step of recognizing that the construction section is located, when the driver turns on the notification switch, it can be recognized that the construction section is located in front.

After recognizing that the construction section is located, the method may further include the step of informing the vehicle occupant that the construction section is located in front of the vehicle and that the construction section will be passed soon.

In the step of monitoring the front vehicle, the position of the front vehicle is tracked among the front images captured by the camera, and when the front vehicle is about to deviate from the front image, the front being tracked within a range where the driving path of the vehicle can be checked. The camera may be rotated along the moving direction of the vehicle.

In the step of setting the expected lane and the target driving path, the expected lane and the target driving path may be set by combining the driving path of the construction section of the vehicle in front and map information on the currently driving road.

In the step of setting the expected lane and the target driving path, the predicted lane and the target driving path may be set using big data-based deep learning.

The present invention effectively sets the driving path that the vehicle must travel in order to safely pass the construction section in spite of various irregular circumstances when the vehicle runs on the construction section of the road, so that it can be driven accordingly, By reducing the possibility of malfunction, the reliability and safety of the vehicle can be greatly improved.

1 is a configuration diagram of an autonomous driving system for a vehicle according to the present invention;
2 is a view illustrating various types of construction signs;
3 is a view illustrating a process in which a vehicle to which the present invention is applied autonomously drives in a construction section;
4 is a flowchart illustrating an embodiment of a method for controlling an autonomous driving system of a vehicle according to the present invention.

Specific structural or functional descriptions of the embodiments of the present invention disclosed in the present specification or application are only exemplified for the purpose of describing the embodiments according to the present invention, and the embodiments according to the present invention may be implemented in various forms. and should not be construed as being limited to the embodiments described in the present specification or application.

Since the embodiment according to the present invention can have various changes and can have various forms, specific embodiments are illustrated in the drawings and described in detail in the present specification or application. However, this is not intended to limit the embodiment according to the concept of the present invention with respect to a specific disclosed form, and should be understood to include all changes, equivalents or substitutes included in the spirit and scope of the present invention.

Terms such as first and/or second may be used to describe various elements, but the elements should not be limited by the terms. The above terms are used only for the purpose of distinguishing one element from another element, for example, without departing from the scope of the present invention, a first element may be called a second element, and similarly The second component may also be referred to as the first component.

When an element is referred to as being “connected” or “connected” to another element, it is understood that it may be directly connected or connected to the other element, but other elements may exist in between. it should be On the other hand, when it is said that a certain element is "directly connected" or "directly connected" to another element, it should be understood that the other element does not exist in the middle. Other expressions describing the relationship between elements, such as "between" and "immediately between" or "neighboring to" and "directly adjacent to", etc., should be interpreted similarly.

The terms used herein are used only to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present specification, terms such as “comprise” or “have” are intended to designate that the described feature, number, step, operation, component, part, or a combination thereof exists, and includes one or more other features or numbers. , it should be understood that it does not preclude the existence or addition of steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having meanings consistent with the context of the related art, and unless explicitly defined in the present specification, they are not to be interpreted in an ideal or excessively formal meaning. .

Hereinafter, the present invention will be described in detail by describing preferred embodiments of the present invention with reference to the accompanying drawings. Like reference numerals in each figure indicate like elements.

Referring to FIG. 1 , an embodiment of an autonomous driving system for a vehicle according to the present invention includes: a camera 1 provided to capture a front image of a vehicle V; Construction notification means (3) for informing that the construction section is located in front of the vehicle (V); A front vehicle tracking unit (5) for monitoring the passing state of the construction section of the front vehicle (VF) photographed with the camera (1); a route setting unit 7 which analyzes the construction section driving path of the front vehicle VF tracked by the front vehicle tracking unit 5 and sets an expected lane and a target driving path; A control unit for receiving information that a construction section is located from the construction notification means (3), controlling the front vehicle tracking unit (5) and the route setting unit (7), and driving the vehicle along the target driving path ( 9) is included.

That is, in the present invention, when a construction section appears in the front while the vehicle V is driving, it is recognized through the construction notification means 3, and the vehicle V is used through the camera 1 and the front vehicle tracking unit 5. First, by monitoring the vehicle ahead (VF) passing through the construction section in front of the , so that the control unit 9 moves the vehicle along the target driving path, so that it can pass the construction section more safely.

The construction notification means 3 may be configured to recognize a construction sign from the front image taken with the camera 1 and notify the control unit 9 that a construction section is located.

In particular, the construction notification means (3) may be configured to recognize the construction sign from the front image taken with the camera (1) by deep learning.

In other words, as exemplified by A and B in FIG. 2, various types of construction signs can be used, so errors are highly likely to occur in a simple comparison of images taken with front images, so CNN (Convolutional Neural Network) It would be desirable to identify construction signs by deep learning such as

The construction notification means 3 as described above can be used for an autonomous driving vehicle at a level where the driver does not board, or an autonomous driving vehicle with a very low level of driver intervention. The location of the construction section in front of the vehicle can be made by the active manipulation of the driver.

That is, the construction notification means 3 may be configured as a notification switch for the driver to confirm that the construction section is located in front and turn it on.

Here, the notification switch may simply mean conventional switches operated by a driver by hand, but a device capable of notifying the control unit 9 about the existence of a construction section ahead by manipulation such as a driver's voice or gesture It should be understood as a concept that also includes

In the above, the function of the construction notification means 3 notifying the control unit 9 that there is a construction section in front of the vehicle has been described. It may be configured to perform a function of notifying the location.

Here, the occupant is a concept including the driver, and informs the driver or other occupants that the construction section is located in front of the vehicle and will then pass through the construction section, so that the risk of accidents is high in the construction section It can have the meaning of allowing the occupants to prepare for driving, and giving the driver an opportunity to choose manual driving for the construction section.

The front vehicle tracking unit 5 tracks the position of the front vehicle VF among the front images captured by the camera 1, and when the front vehicle VF is about to deviate from the front image, the vehicle V ) may be configured to rotate the camera 1 along the moving direction of the forward vehicle VF being tracked within a range in which the driving path can be checked.

That is, when the forward vehicle tracking unit 5 tracks the movement path of the front vehicle (VF) passing through the construction section as a whole as possible, the path setting unit 7 can more accurately set the expected lane and target driving path. Therefore, as shown in D of FIG. 3 , the camera 1 is rotated to continuously track the front vehicle VF.

Of course, if there are a plurality of cameras 1 capable of photographing the front of the vehicle V, tracking of the vehicle VF in front and checking the driving route of the vehicle V may be operated separately, In the case of only one, as described above, the camera 1 is rotated toward the front vehicle VF being tracked as much as possible within the range where the driving route of the vehicle can be checked.

On the other hand, the front vehicle tracking unit 5 tracks the position of the front vehicle VF among the front images captured by the camera 1, and when the front vehicle VF tries to deviate from the front image, configured to provide information to the control unit (9); The control unit 9 rotates the camera 1 according to the moving direction of the front vehicle VF being tracked within the range in which the driving path of the vehicle can be checked according to the information from the front vehicle tracking unit 5. It can be configured to

That is, instead of allowing the front vehicle tracking unit 5 to directly rotate the camera 1 , rotation control of the camera 1 allows the control unit 9 to request or information from the front vehicle tracking unit 5 . to be performed according to

The route setting unit 7 is configured to set the expected lane and target travel route by combining the construction section travel route of the front vehicle VF and map information on the road currently being driven.

That is, the route setting unit 7 calculates the position and driving direction of the vehicle VF on the basis of the position and driving direction of the vehicle V on the map of the road being driven, and calculates the position and driving direction of the vehicle VF on the map of the construction section. to set the route through which the vehicle in front (VF) has passed and the expected lane of the construction section based on it.

The route setting unit 7 may be configured to set the expected lane and target driving route by using big data-based deep learning.

In other words, while passing through the construction section, the condition or shape of surrounding obstacles, road surfaces, and lanes are not marked or the condition changes in various ways, and when the vehicle in front (VF) passes through this section, Since the appearance is different and diverse from the driving situation of the general road, using deep learning based on big data for this situation, the driving route of the construction section of the vehicle in front (VF) is analyzed, and the expected lane and target to set the driving route.

A process of autonomous driving in a construction section of a vehicle to which the present invention is applied will be described with reference to FIG. 3 .

A indicates that the vehicle (VF) in front of the vehicle (V) is entering the construction section, and the lane is not marked in the construction section, and the construction notification means (3) indicates that the construction section is located in front of the vehicle It is recognized by , and the driving situation of the vehicle in front (VF) is photographed with the camera 1 and monitored.

B and C show the situation in which the front vehicle (VF) is passing through the construction section in turn, and in the vehicle (V), while the front vehicle (VF) is passing through the construction section, the front vehicle tracking unit By means of (5), while monitoring the vehicle in front (VF), an expected lane and a target driving route are set with the route setting unit (7).

In D, the vehicle V starts driving along the target driving route in the construction section, and as described above, the camera 1 is rotated so that the vehicle VF can be continuously tracked. It expresses the state together.

4 is a flowchart illustrating an embodiment of a method for controlling an autonomous driving system of a vehicle according to the present invention, comprising: photographing a front image of the vehicle with a camera 1 ( S10 ); Recognizing that the construction section is located in front of the vehicle (S20); monitoring the passing condition of the construction section of the front vehicle (VF) photographed with the camera (1) (S30); setting an expected lane and a target driving path by analyzing the driving path in the construction section of the monitored vehicle in front (VF) (S40); and driving the vehicle along the target driving path (S50).

In the step (S20) of recognizing that the construction section is located, a construction sign is recognized from the front image captured by the camera 1, so that it can be recognized that the construction section is located in front of the vehicle.

In the step (S20) of recognizing that the construction section is located, it is possible to recognize the construction sign by deep learning from the front image taken with the camera (1).

In the step of recognizing that the construction section is located (S20), when the driver turns on the notification switch, it can be recognized that the construction section is located in front.

After the step of recognizing that the construction section is located (S20), the method may further include a step (S25) of informing the vehicle occupant that the construction section is located in front of the vehicle and will soon pass through the construction section.

In the step (S30) of monitoring the front vehicle (VF), the position of the front vehicle (VF) is tracked among the front images captured by the camera (1), and the front vehicle (VF) is about to deviate from the front image. In this case, the camera 1 may be rotated along the moving direction of the forward vehicle VF being tracked within a range in which the driving path of the vehicle can be checked.

In the step of setting the expected lane and target driving path (S40), the expected lane and target driving path may be set by combining the construction section driving path of the vehicle in front (VF) and map information on the currently driving road. .

In the step of setting the expected lane and the target driving path ( S40 ), the predicted lane and the target driving path may be set using big data-based deep learning.

Although the present invention has been shown and described with reference to specific embodiments, it is within the art that the present invention can be variously improved and changed without departing from the spirit of the present invention provided by the following claims. It will be obvious to those of ordinary skill in the art.

One; camera
3; Construction notification means
5; front vehicle tracking
7; route setting unit
9; control
V; vehicle
VF; front vehicle

Claims (17)

a camera provided to take an image of the front of the vehicle;
Construction notification means for notifying that the construction section is located in front of the vehicle;
a front vehicle tracking unit for monitoring the passing situation of the front vehicle photographed with the camera;
a route setting unit for setting an expected lane and a target driving route by analyzing the driving route of the construction section of the front vehicle tracked by the front vehicle tracking unit;
a control unit receiving information that a construction section is located from the construction notification means, controlling the front vehicle tracking unit and the path setting unit, and driving the vehicle along the target driving path;
An autonomous driving system for a vehicle, characterized in that it comprises a. The method according to claim 1,
The construction notification means is configured to recognize the construction sign from the front image taken with the camera and notify the control unit that the construction section is located
An autonomous driving system for a vehicle, characterized in that 3. The method according to claim 2,
The construction notification means is configured to recognize the construction sign by deep learning from the front image taken with the camera
An autonomous driving system for a vehicle, characterized in that The method according to claim 1,
The construction notification means is composed of a notification switch that turns on the driver after confirming that the construction section is located in front
An autonomous driving system for a vehicle, characterized in that The method according to claim 1,
The construction notification means is configured to notify the occupant of the vehicle that the construction section is located in front of the vehicle.
An autonomous driving system for a vehicle, characterized in that The method according to claim 1,
The front vehicle tracking unit tracks the position of the front vehicle among the front images captured by the camera, and when the front vehicle is about to deviate from the front image, the moving direction of the front vehicle being tracked within the range where the driving path of the vehicle can be checked configured to rotate the camera along
An autonomous driving system for a vehicle, characterized in that The method according to claim 1,
the front vehicle tracking unit is configured to track the position of the front vehicle among the front images captured by the camera, and to provide information about the front vehicle to the control unit when the front vehicle is about to deviate from the front image;
The control unit is configured to rotate the camera along the moving direction of the front vehicle being tracked within a range in which the driving path of the vehicle can be checked according to the information from the front vehicle tracking unit.
An autonomous driving system for a vehicle, characterized in that The method according to claim 1,
The route setting unit is configured to set the expected lane and target travel route by combining the driving route for the construction section of the front vehicle and map information on the road currently being driven
An autonomous driving system for a vehicle, characterized in that 9. The method of claim 8,
The route setting unit is configured to set the expected lane and target driving route using big data-based deep learning
An autonomous driving system for a vehicle, characterized in that photographing a front image of the vehicle with a camera;
Recognizing that the construction section is located in front of the vehicle;
monitoring the condition of passing the construction section of the front vehicle photographed with the camera;
setting an expected lane and a target driving path by analyzing the driving path in the construction section of the monitored vehicle in front;
driving the vehicle along the target driving path;
A method for controlling an autonomous driving system of a vehicle, comprising: 11. The method of claim 10,
In the step of recognizing that the construction section is located, by recognizing the construction sign from the front image taken with the camera, recognizing that the construction section is located in front of the vehicle
A method for controlling an autonomous driving system of a vehicle, characterized in that 12. The method of claim 11,
In the step of recognizing that the construction section is located, recognizing the construction sign from the front image taken with the camera by deep learning
A method for controlling an autonomous driving system of a vehicle, characterized in that 11. The method of claim 10,
In the step of recognizing that the construction section is located, when the driver turns on the notification switch, recognizing that the construction section is located in front
A method for controlling an autonomous driving system of a vehicle, characterized in that 11. The method of claim 10,
After recognizing that the construction section is located, further comprising the step of notifying the vehicle occupant that the construction section is located in front of the vehicle and that the construction section will be passed soon
A method of controlling an autonomous driving system of a vehicle, characterized in that 11. The method of claim 10,
In the step of monitoring the front vehicle, the position of the front vehicle is tracked among the front images captured by the camera, and when the front vehicle is about to deviate from the front image, the front being tracked within a range where the driving path of the vehicle can be checked. rotating the camera along the direction of movement of the vehicle;
A method for controlling an autonomous driving system of a vehicle, characterized in that 11. The method of claim 10,
In the step of setting the expected lane and the target driving path, setting the expected lane and the target driving path by combining the driving path of the construction section of the vehicle in front and map information on the currently driving road
A method of controlling an autonomous driving system of a vehicle, characterized in that 17. The method of claim 16,
In the step of setting the expected lane and target driving path, setting the expected lane and target driving path using big data-based deep learning
A method of controlling an autonomous driving system of a vehicle, characterized in that

Images