KR102499975B1 - Vehicle, and control method for the same - Google Patents

Abstract

A vehicle according to an embodiment of the disclosed invention includes a distance sensor that collects data on the surrounding environment of the vehicle in order to detect curb information by performing fast data processing while considering the geometry of the curb; a storage unit that receives and stores map information; Curb-related information is extracted using the data received from the distance sensor, the vehicle position is determined by comparing the curb-related information and the curb-stone information on the map, and driving is possible based on the curb-related information and the vehicle position. a control unit that determines an area and creates a driving route; and a driving unit that receives the driving route generated by the control unit and drives the vehicle according to the driving route.

Description

Vehicle and its control method {VEHICLE, AND CONTROL METHOD FOR THE SAME}

Vehicle and control for detecting curb information by performing fast data processing while considering the curb geometry, recognizing the current location of the vehicle based on the curb information, and generating a driving route using the curb information and vehicle location information It's about how.

An unmanned self-driving vehicle detects obstacles located in the traveling direction in order to drive safely, and determines the driving direction using the detected information. At this time, the unmanned self-driving vehicle should not collide with obstacles formed on the ground or obstacles present in the direction of travel. For example, when an unmanned autonomous vehicle drives on a roadway, it is necessary to avoid a collision by detecting a curbstone that is a boundary stone between a roadway and a sidewalk or a roadway in the opposite direction.

In the method of detecting such a curb, conventionally, if the height of the curb measured by the sensor using a threshold value for the height of the curb is above a certain value, the curb is determined as a curb or a normal vector formed with the wall surface of the curb is obtained. A method of detecting that the wall surface of the wall faces the road direction was used.

However, since the method using the threshold value for the height of the curb simply uses only the value for the height, it is difficult to accurately detect the curb, and there is a problem of performance degradation due to noise. In addition, in the case of a method for detecting that the curb wall faces toward the road, there is a problem in that other wall surfaces may be detected in addition to the curb wall surface.

Therefore, a technique for quickly and accurately detecting curbstone information considering the curbstone geometry is required.

One aspect provides a vehicle and a control method for quickly and accurately detecting curb information considering the geometric structure of the curb.

Another aspect provides a vehicle and a control method for determining a current location of a vehicle by comparing detected curb information with curb information of an actual map.

Another aspect provides a vehicle and a control method for determining a drivable area by using detected curb information and vehicle position and generating an appropriate driving path.

As a technical means for achieving the above-described technical problem, a vehicle according to an aspect includes a distance sensor for collecting data on a vehicle's surrounding environment; a storage unit that receives and stores map information; Curb-related information is extracted using the data received from the distance sensor, the vehicle position is determined by comparing the curb-related information and the curb-stone information on the map, and driving is possible based on the curb-related information and the vehicle position. a control unit that determines an area and creates a driving route; and a driving unit that receives the driving path generated by the control unit and drives the vehicle according to the driving path.

Also, the curb-related information may include a curb candidate point, a curb point, or a curb line.

In addition, the control unit projects the data received from the distance sensor onto a specific plane, extracts curb candidate points from the specific plane, determines whether the extracted curb curb points satisfy specific conditions, and determines curb points and curb lines. can create

In addition, the control unit projects the data as a plurality of points on a plane parallel to the ground, sets two points at regular intervals as a starting point to generate a straight line equation, and points belonging to a normal distribution based on the straight line equation It is possible to extract curb candidate points by detecting .

In addition, the control unit may determine that the curb candidate point is valid when a condition is satisfied, on the condition that a plurality of points located within a predetermined distance from the straight line according to the straight line equation exist on both sides of the straight line.

In addition, the control unit projects the curb candidate point on a plane parallel to the side of the curb, and determines that the curb candidate point is valid when the condition is satisfied on the condition that the height value of the curb candidate point simply increases or decreases. can do.

In addition, the control unit may determine that the curb candidate point is valid if the condition is satisfied, on the condition that the heights of the plurality of points existing on both sides of the straight line are higher or lower than the height of the curb candidate point.

Also, the control unit may determine an effective curb point as a curb point and generate a curb line using the curb point.

Also, the control unit may determine the current location of the vehicle by matching the curb information of the map with the curb point.

In addition, the control unit determines a drivable area based on the curb line and the vehicle position, generates a driving path of the vehicle within the drivable area, and determines the suitability of the driving path based on risk factors present in the driving path. is determined, and if it is unsuitable, an avoidance path may be created in consideration of the curb line.

A vehicle control method according to another aspect includes collecting data on an environment around the vehicle; Receiving and storing map information; Extracting information about the curb using the collected data; determining the location of the vehicle by comparing the curb information with curb information on a map; determining a drivable area based on the curb information and the vehicle position and generating a driving route; and driving the vehicle according to the driving route.

Also, the curb-related information may include a curb candidate point, a curb point, or a curb line.

In addition, the step of extracting the information about the curb may include projecting the data on a specific plane; extracting curb candidate points on a specific plane onto which the data is projected; and generating curb points and curb lines by determining whether the extracted curb candidate points satisfy a specific condition.

In addition, the step of projecting the data on a specific plane projects the data as a plurality of points on a plane parallel to the ground, and the step of extracting the consecutive candidate points sets two points at regular intervals as starting points to obtain a straight line equation. and a curb candidate point can be extracted by detecting points belonging to a normal distribution based on the straight line equation.

In addition, the step of generating the curb point and the curb line is based on the condition that a plurality of points located within a certain distance from the straight line by the straight line equation exist on both sides of the straight line, when the condition is satisfied, the curb candidate point is valid It may further include; step of determining that.

In addition, in the step of projecting the data onto a specific plane, the candidate curb point is projected onto a plane parallel to the side of the curb, and in the step of generating the curb point and the curb line, the height value of the candidate curb point is simply increased. Alternatively, the method may further include determining that the curb candidate point is valid if the condition is satisfied on the condition that the point is simply decreased.

In addition, in the generating of the curb point and the curb line, the height of the plurality of points on both sides of the straight line is higher or lower than the height of the curb candidate point, and when the condition is satisfied, the curb candidate point is selected. It may further include; determining that it is valid.

In the generating of the curb point and the curb line, an effective curb candidate point may be determined as a curb point, and a curb line may be generated using the curb point.

In addition, the projecting the data onto a specific plane projects the curb candidate points onto a plane parallel to the side of the curb, and the generating of the curb points and curb lines may cause a height value of the curb candidate point to simply increase or decrease. The method may further include determining that the curb candidate point is valid if a condition is satisfied on the condition that the point is simply decreased.

In addition, in the generating of the curb point and the curb line, the height of the plurality of points on both sides of the straight line is higher or lower than the height of the curb candidate point, and when the condition is satisfied, the curb candidate point is selected. It may further include; determining that it is valid.

In the generating of the curb point and the curb line, an effective curb candidate point may be determined as a curb point, and a curb line may be generated using the curb point.

The determining of the location of the vehicle may further include determining the current location of the vehicle by matching curb information on the map with the curb point.

The generating of the driving path may include determining a drivable area based on the curb line and the vehicle position; generating a travel path of the vehicle within the drivable area; and determining suitability of the driving route based on risk factors present in the driving route, and generating an avoidance route in consideration of the curb line when the driving route is unsuitable.

According to the vehicle and the control method according to one aspect, it is possible to quickly and accurately detect curb information considering the geometric structure of the curb.

According to a vehicle and a control method thereof according to another aspect, a current location of the vehicle may be determined by comparing detected curb information with curb information of an actual map.

According to a vehicle and a control method thereof according to another aspect, a drivable area may be determined using detected curb information and a vehicle position, and an appropriate driving route may be generated.

1 is a view showing the appearance of a vehicle according to an exemplary embodiment.
2 is a diagram showing an internal configuration of a vehicle according to an embodiment.
3 is a diagram illustrating a control block of a vehicle according to an exemplary embodiment.
4 is a diagram illustrating an example in which a vehicle projects data received from a distance sensor onto a specific plane according to an exemplary embodiment.
5 is a view illustrating extracting curb-related information by projecting data as a plurality of points on an XY plane by a vehicle according to an exemplary embodiment.
FIG. 6 is a diagram illustrating extracting information about a curb by projecting data onto an XZ plane by a vehicle according to an exemplary embodiment.
FIG. 7 is a diagram for explaining how a vehicle determines validity of information about a curb extracted from an XY plane according to an exemplary embodiment.
FIG. 8 is a diagram for explaining how a vehicle determines validity of information about a curb extracted from an XZ plane according to an exemplary embodiment.
9 is a diagram illustrating an example of determining a current location of a vehicle according to an exemplary embodiment.
10 is a diagram for explaining an example in which a vehicle determines a drivable area and generates a driving path according to an exemplary embodiment.
11 to 13 are flowcharts of a method for controlling a vehicle according to an exemplary embodiment.

Like reference numbers designate like elements throughout the specification. This specification does not describe all elements of the embodiments, and general content or overlapping content between the embodiments in the technical field to which the present invention belongs is omitted. The term 'unit, module, member, or block' used in the specification may be implemented as software or hardware, and according to embodiments, a plurality of 'units, modules, members, or blocks' may be implemented as one component, It is also possible that one 'part, module, member, block' includes a plurality of components.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case of being directly connected but also the case of being indirectly connected, and indirect connection includes being connected through a wireless communication network. do.

In addition, when a certain component is said to "include", this means that it may further include other components without excluding other components unless otherwise stated.

Terms such as first and second are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

Expressions in the singular number include plural expressions unless the context clearly dictates otherwise.

In each step, the identification code is used for convenience of description, and the identification code does not explain the order of each step, and each step may be performed in a different order from the specified order unless a specific order is clearly described in context. there is.

Hereinafter, the working principle and embodiments of the present invention will be described with reference to the accompanying drawings.

1 is a view showing the exterior of a vehicle according to an embodiment, and FIG. 2 is a view showing the inside of a vehicle according to an embodiment.

Referring to FIG. 1, the exterior of a vehicle 1 includes a main body 10 forming the exterior of the vehicle 1, a windscreen 11 providing a driver with a view of the front of the vehicle 1, and a driver A side mirror 12 providing a rear view of the vehicle 1, a door 13 shielding the inside of the vehicle 1 from the outside, and a front wheel 21 located in front of the vehicle 1, It may include a rear wheel 22 located at the rear, and these front wheels 21 and 22 may be collectively referred to as wheels.

The wind screen 11 is provided on the front upper side of the main body 10 so that the driver inside the vehicle 1 can obtain visual information of the front of the vehicle 1. In addition, the side mirror 12 includes a left side mirror provided on the left side of the body 10 and a right side mirror provided on the right side of the body 10, and the driver inside the vehicle 1 provides visual information of the side and rear of the vehicle 1. make it possible to obtain

Doors 13 are rotatably provided on the left and right sides of the main body 10 so that the driver can get inside the vehicle 1 when opened, and when closed, the inside of the vehicle 1 is shielded from the outside. can

In addition, the vehicle 1 may include a distance sensor 100 installed on the front panel 14 to collect data on the surrounding environment of the vehicle. The distance sensor 100 may be mounted in the front radiator grille or the front headlamp of the vehicle 1, and there is no limitation on its location.

The distance sensor 100 may be a sensor that measures a distance to the environment at regular intervals, such as a laser scanner, an infrared scanner, or a 3D LiDAR sensor. A 3D lidar sensor is a sensor capable of detecting distance, direction, speed, temperature, material distribution and concentration characteristics to a target by irradiating a laser onto the target.

The distance sensor 100 transmits the acquired data to the control unit 300, and the control unit 300 analyzes the data received from the distance sensor 100 to perform curb detection, vehicle location recognition, and driving path generation. . The control unit 300 detecting the curb, recognizing the location of the vehicle, and generating the driving path will be described in detail with reference to FIGS. 3 to 13 below.

Referring to FIG. 2 , the interior 120 of the vehicle body is disposed on the seat 121 (121a, 121b) on which the occupant sits, the dashboard 122, and the dashboard, and includes a tachometer, a speedometer, a coolant temperature gauge, a fuel gauge, and a direction indicator. An instrument panel (i.e., a cluster 123) in which a shift indicator light, a high beam indicator light, a warning light, a seat belt warning light, an odometer, an odometer, an automatic shift selection lever indicator, a door open warning light, an engine oil warning light, and a low fuel warning light are disposed, and a vehicle It includes a steering wheel 124 for manipulating the traveling direction of the vehicle, and a center fascia 125 with a control panel for an audio device and an air conditioner.

The seat 121 includes a driver's seat 121a where the driver sits, a passenger seat 121b where the passenger sits, and a rear seat located at the rear of the vehicle.

Cluster 123 can be implemented digitally. This digital cluster displays vehicle information and driving information as images.

The center fascia 125 is located between the driver's seat 121a and the front passenger's seat 121b in the dashboard 122 and includes an audio device, an air conditioner, and a head unit 126 that controls seat heating.

Here, the head unit 126 may include a plurality of button units for receiving operation commands of the audio device, the air conditioning device, and the heating wire of the seat.

An air outlet, a cigar jack, and the like may be installed in the center fascia 125, and a multi-terminal 127 may be installed.

Here, the multi-terminal 127 may be disposed adjacent to the head unit 126, include a USB port and an AUX terminal, and may further include an SD slot.

The vehicle 1 may further include an input unit 128 for receiving operation commands of various functions, and may further include a display unit 129 displaying information on functions being performed and information input by a user. .

The display panel of the display unit 129 may employ a light emitting diode (LED) panel, an organic light emitting diode (OLED) panel, or a liquid crystal display (LCD) panel.

The input unit 128 may be provided on the head unit 126 and the center fascia 125, and includes at least one physical button such as an on/off button for operating various functions and a button for changing the setting values of various functions. do.

The input unit 128 may transmit button operation signals to an electronic control unit (ECU), a controller 300 in the head unit 126, or an AVN device 130.

The input unit 128 may include a touch panel integrally provided with the display unit of the AVN device 130 . The input unit 128 may be activated and displayed in the form of a button on the display unit of the AVN device 130, and at this time, position information of the displayed button is input.

The input unit 128 may further include a jog dial (not shown) or a touch pad for inputting a cursor movement command and a selection command displayed on the display unit of the AVN device 130 . Here, the jog dial or touch pad may be provided in a center fascia or the like.

More specifically, the input unit 128 can receive an input of either a manual driving mode in which a driver directly drives a vehicle or an autonomous driving mode, and when the autonomous driving mode is input, an input signal of the autonomous driving mode is sent to the control unit 300. send to

In addition, the input unit 128 receives destination information when the navigation function is selected, transmits the input destination information to the AVN device 130, receives channel and volume information when the DMB function is selected, and transmits the input channel and volume information. It is transmitted to the AVN device 130.

An AVN device 130 that receives information from a user and outputs a result corresponding to the input information may be provided in the center fascia 125 .

The AVN device 130 may perform at least one of a navigation function, a DMB function, an audio function, and a video function, and display environment information and driving information of a road in an autonomous driving mode.

The AVN device 130 may be mounted on a dashboard.

The chassis of the vehicle further includes a power generating device, a power transmission device, a traveling device, a steering device, a braking device, a suspension device, a transmission device, a fuel device, front and rear wheels, and the like. In addition, the vehicle further includes various safety devices for driver and occupant safety.

Vehicle stability devices include an airbag control device for the safety of passengers such as the driver in case of a vehicle collision, and an electronic stability control (ESC) that adjusts the vehicle's posture during vehicle acceleration or cornering. There are devices.

In addition, the vehicle 1 includes a proximity sensor for detecting rear or side obstacles or other vehicles, a rain sensor for detecting whether or not there is precipitation and the amount of precipitation, a wheel speed sensor for detecting the wheel speed of the vehicle, and a lateral acceleration for detecting the lateral acceleration of the vehicle. It is possible to further include detection devices such as an acceleration sensor, a yaw rate sensor that detects a change in the angular velocity of the vehicle, a gyro sensor, and a steering angle sensor that detects rotation of a steering wheel of the vehicle.

Such a vehicle 1 is an electronic control unit (ECU) that controls driving of a power generating device, a power transmission device, a traveling device, a steering device, a braking device, a suspension device, a transmission device, a fuel device, various safety devices, and various sensors. Electronic Control Unit).

In addition, the vehicle 1 may optionally include electronic devices installed for driver's convenience, such as a hands-free device, a GPS, an audio device and a Bluetooth device, a rear camera, a terminal device charging device, and a high-pass device.

The vehicle 1 may further include a starting button for inputting an operation command to a starting motor (not shown).

That is, when the start button is turned on, the vehicle 1 operates a starter motor (not shown) and drives an engine (not shown) as a power generating device through the operation of the starter motor.

The vehicle 1 further includes a battery (not shown) electrically connected to terminal devices, audio devices, indoor lights, a starter motor, and other electronic devices to supply driving power. The battery is charged using its own generator or engine power while driving.

3 is a diagram illustrating a control block of a vehicle according to an exemplary embodiment.

Referring to FIG. 3 , first, the distance sensor 100 collects data on the surrounding environment of the vehicle. Data on the surrounding environment of the vehicle includes data on a curb as data on objects existing around the vehicle.

When the distance sensor 100 is a 3D LiDAR sensor, the distance sensor 100 calculates the distance to an object by emitting a laser pulse signal and measuring the arrival time of reflected pulse signals from objects within a measurement range. can be measured That is, the distance sensor 100 may collect data about the distance to the curb within the measurement range. While the vehicle 1 is driving, the distance sensor 100 collects data on the distance to the curb in real time. At this time, the distance sensor 100 collects 3D data reflecting the geometric structure of the curb.

A plurality of distance sensors 100 may be used. When a plurality of distance sensors 100 are used, synchronization between the distance sensors is performed.

The storage unit 200 may receive and store map information from the outside. The map is a map containing information about the real environment around the vehicle, and the map information includes information about the actual characteristics of the curb. The curb information included in the map is used in a step of recognizing the current location of the vehicle, which will be described later. The storage unit 200 may store current location information of the vehicle.

The control unit 300 extracts curb-related information using the data received from the distance sensor 100, compares the curb-related information with curb information on a map to determine the vehicle location, and determines the curb-related information and vehicle location. Based on this, it is possible to determine a driving area and create a driving route.

Here, the curb-related information includes a curb candidate point, a curb point, or a curb line, and data collected by the distance sensor 100 may be projected onto a specific plane and displayed in the form of a dot or a line. In addition, the information on the curbstone may be grasped in the same meaning as the curbstone characteristics described in FIGS. 11 to 13 . A more detailed description of the curb candidate point, curb point, or curb line will be described later.

The controller 300 includes a curb detector 400, a location recognizer 500, and a path generator 600. Specifically, the curb detection unit 400 extracts curb-related information using data received from the distance sensor 100, and the location recognition unit 500 compares the curb-related information with curb information on a map to locate the vehicle. , and the route creation unit 600 determines a drivable area based on the information on the curb and the location of the vehicle and creates a driving route.

The curb detection unit 400 may further include a data acquisition unit 410, a view conversion unit 420, a feature extraction unit 430, and a data determination unit 440. The data acquisition unit 410 receives data collected by the distance sensor 100 .

A method of detecting a curbstone by the curbstone detector 400 will be described in detail with reference to FIGS. 4 to 8 below.

4 is a diagram illustrating an example in which a vehicle projects data received from a distance sensor onto a specific plane according to an exemplary embodiment.

Referring to FIG. 4 , the view conversion unit 420 projects the data received by the data acquisition unit 410 onto a specific plane. Here, the specific plane refers to an XY plane, which is a plane parallel to the ground, or an XZ plane, which is a plane parallel to the side of the curb, when the traveling direction of the vehicle in the three-dimensional coordinate system (X, Y, Z) is referred to as the X direction. The curb side is the curb surface perpendicular to the ground.

The view conversion unit 420 may project the data received by the data acquisition unit 410 on the XY plane or the XZ plane in the form of a plurality of dots. The view conversion unit 420 projects the data onto the XY plane and the XZ plane, so that information on the curb considering the geometric structure of the curb can be extracted.

When the distance sensor 100 is a 3D LiDAR sensor, since the LiDAR sensor emits a laser signal in a circular shape, when the data on the side of the curb is projected onto the XY plane, a plurality of points form a straight line. When projected on the XZ plane, a plurality of points appear to have an inclination.

A method of extracting information about a curb from a plurality of points projected on a specific plane by the feature extractor 430 will be described with reference to FIGS. 5 and 6 .

5 is a view illustrating extracting curb-related information by projecting data to a plurality of points on an XY plane by a vehicle according to an embodiment, and FIG. 6 is a diagram illustrating a vehicle projecting data onto an XZ plane according to an embodiment It is a diagram explaining the extraction of information about the curb by using

The feature extractor 430 may extract information about a curb on a specific plane on which data collected by the distance sensor 100 is projected as a plurality of points. At this time, the feature extractor 430 extracts curb candidate points from among curb-related information. Here, the curb candidate point means a point that can be determined as a point corresponding to the side of the curb among a plurality of points projected on a specific plane.

Referring to FIG. 5, when the data collected by the distance sensor 100 is projected onto the XY plane, the feature extractor 430 sets two points at regular intervals as starting points (①) to generate a straight line equation (② ), and extracts curb candidate points by detecting (③, ④) the points belonging to the normal distribution based on the linear equation. When all the points belonging to the normal distribution are detected on the straight line generated by the straight line equation, move to the next point and repeat the steps ① to ④ (⑤).

Referring to FIG. 6 , after the feature extractor 430 extracts curb candidate points on the XY plane, the view conversion unit 420 projects the data onto the XZ plane, and the feature extractor 430 calculates the height of the curb candidate points value and height values of a plurality of points existing on both sides of the straight line are extracted. Since the LiDAR sensor emits a laser signal in a circular shape, data on the side of the curb is detected as having an inclination, and therefore, the height values of each of the curb candidate points may be different.

A method for the data determination unit 440 to determine the validity of the information about the curb extracted from a specific plane will be described with reference to FIGS. 6 to 8 .

FIG. 7 is a view for explaining that a vehicle determines validity of information about a curb extracted from an XY plane according to an embodiment, and FIG. 8 is a view illustrating information about a curb extracted from a vehicle on an XZ plane according to an embodiment. It is a drawing explaining the determination of validity.

The data determination unit 440 determines whether the extracted curb candidate points satisfy a specific condition to determine validity of the curb candidate points, and may generate curb points and curb lines accordingly.

The data determination unit 440 conditions whether a plurality of points located at a certain distance from the straight line generated by the feature extraction unit 430 in the XY plane exist on both sides of the straight line, and if the condition is satisfied, the curb candidate point is considered valid judge

Referring to FIG. 7 , a plurality of points ② and ③ exist on both sides of a straight line ① generated by the feature extraction unit 430 on the XY plane. As described above, since the laser signal is emitted in a circular shape due to the characteristics of the LiDAR sensor, the curb candidate point, which is information about the side of the curb, appears as a straight line in the XY plane, and the sidewalk and roadway separated by the curb side. Information about the plane is represented by another plurality of points on either side of the straight line.

That is, a curb candidate point is valid only when there are a plurality of points connected to both ends of a straight line created by connecting the curb candidate points in the XY plane and located in opposite directions to each other. When a plurality of points existing on both sides of the straight line are not detected, the data determination unit 440 determines that the curb candidate points are not valid and causes the distance sensor 100 to collect data again.

In addition, referring to FIG. 6, the data determination unit 440 determines whether the height value of the curb candidate point extracted by the feature extraction unit 430 in the XZ plane simply increases or decreases, and when the condition is satisfied, the curb candidate Points are considered valid.

As described above, due to the characteristics of the LiDAR sensor that emits the laser sensor in a circular shape, the height of the curb candidate point projected on the XZ plane must be simply increased or simply decreased, so the value of the curb candidate point height value is simply increased Alternatively, the validity of the curb candidate points may be determined based on a simple reduction.

If the height value of the curb candidate point does not simply increase or simply decrease, the data determination unit 440 determines that the curb candidate point is invalid and causes the distance sensor 100 to collect data again.

Additionally, the data determination unit 440 determines whether the heights of a plurality of points on both sides of the straight line are higher or lower than the height of the curb candidate point, and determines the curb candidate point as valid when the condition is satisfied.

Referring to FIG. 8 , a plurality of points existing on both sides of a straight line in the XY plane appear higher or lower than the height of the curb candidate point in the XZ plane. Since the plurality of points on both sides of the straight line in the XY plane represent the sidewalk or roadway separated by the curb side, the heights of the points on both sides of the straight line appear higher or lower than the height of the curb candidate point.

If the heights of a plurality of points on both sides of the straight line are not maintained higher or lower than the height of the curb candidate points, the data determination unit 440 determines that the curb candidate points are invalid and causes the distance sensor 100 to send the data again. to collect

When the extracted curb candidate points satisfy all of the above conditions, the data determination unit 440 determines the curb candidate points as curb points and creates a curb line by connecting the curb point points. The curb line can be created as a quadratic curved line.

At this time, a RANdom SAmple Consensus (RANSAC) algorithm may be utilized to connect the curb points. The RANSAC algorithm is an algorithm that selects the data that forms the maximum consensus from randomly selected sample data. By utilizing the RANSAC algorithm, it is possible to approximate the curb line even if there is an outlier out of the normal distribution among the curb points. Since the RANSAC algorithm is a well-known algorithm, description of its specific structure is omitted.

As the curb detector 400 detects curb-related information through the above-described process, curb-stone information considering the geometric structure of the curb can be quickly and accurately detected.

Referring back to FIG. 3 , the location recognition unit 500 includes a map information processing unit 510, a data processing unit 520, and a location determination unit 530. The location recognition unit 500 may compare map information stored in the storage unit 200 with curb-related information to determine the location of the vehicle.

A method of determining the current location of the vehicle by the location recognition unit 500 will be described with reference to FIG. 9 .

9 is a diagram illustrating an example of determining a current location of a vehicle according to an exemplary embodiment.

Referring to FIG. 9 , the map information processing unit 510 receives map information from the storage unit 200 and receives curb point and curb line information from the curb detection unit 400 .

The data processor 520 extracts curb information from the map information received by the map information processor 510 . The map includes information such as the shape and location of an actual curb, may be a 2D or 3D map, and may include Global Positioning System (GPS) information. In FIG. 9 , thick gray lines indicate curbs extracted from the map, and points indicated by dots in a plurality of dotted line boxes indicate curb points detected by the curb detection unit 400 .

The location determining unit 530 determines the current location of the vehicle by matching the curb point received by the map information processing unit 510 with the curb information on the map. The location determination unit 530 may update the current location of the vehicle by transmitting it to the storage unit 200 .

Since the current location of the vehicle on the road can be recognized by comparing the curb point detected by the curb detection unit 400 with the curb information on the map, the location of the vehicle can be identified even when the lane is blurred or erased.

Referring back to FIG. 3 , the driving route creation unit 600 includes a drivable area determination unit 610 , a route generation unit 620 , and a risk determination unit 630 . A method in which the driving route generator 600 determines the drivable area and generates the driving route will be described with reference to FIG. 10 .

10 is a diagram for explaining an example in which a vehicle determines a drivable area and generates a driving path according to an exemplary embodiment.

Referring to FIG. 10 , the drivable area determination unit 610 receives information on the curb line and the vehicle position and determines the drivable area based on the curb line and the vehicle position. That is, the drivable area determining unit 610 may determine the drivable area of the vehicle with the curb line generated by the curb detecting unit 400 as a boundary. In FIG. 9 , a gray shaded and oblique line corresponds to a curb line.

The path generator 620 creates a driving path of the vehicle within a drivable area. The vehicle may drive along the generated driving route.

The risk determination unit 630 determines suitability of the driving route based on risk factors present in the generated driving route. The risk determining unit 630 may determine that the driving path is unsuitable by determining that smooth driving of the vehicle is difficult when obstacles or other vehicles exist on the driving path. In addition, the risk determination unit 630 may determine that the driving route is unsuitable even when an unexpected situation occurs while the vehicle is driving and the vehicle deviate from the existing route.

When the risk determining unit 630 determines that the driving path is unsuitable, the path generating unit 620 creates an avoidance path by considering the curb line. In FIG. 9 , a line indicated by an arrow and a dotted line corresponds to an avoidance path created by considering the curb line.

As described above, by determining the drivable area of the vehicle and generating the driving route, it is possible to respond to an unexpected situation while driving and to promote safer driving.

The driving unit 700 may receive a driving path from the driving path generator 600 and drive the vehicle. The driving unit 700 may transmit driving signals to various devices such as a power generation device, a power transmission device, a traveling device, a steering device, a braking device, a suspension device, and a transmission device of a vehicle.

11 to 13 are flowcharts of a method for controlling a vehicle according to an exemplary embodiment.

Referring to FIG. 11 , the controller 300 according to an exemplary embodiment receives data about the environment around the vehicle collected by the distance sensor 100 ( 1210 ). The controller 300 projects the received data as a plurality of points on the XY plane, which is a plane parallel to the ground, to perform view conversion (1220), and from the plurality of points projected on the XY plane, curb candidate points among curb-related information Extract (1230).

At this time, the consecutive candidate points are extracted through a process of generating a linear equation by setting two points at regular intervals as starting points and detecting points belonging to a normal distribution based on the linear equation.

The controller 300 determines whether curb candidate points, which are extracted curb features, satisfy a specific condition (1240). Here, a specific condition is whether a plurality of points located within a certain distance from a straight line by a straight line equation exist on both sides of the straight line, and when the condition is satisfied, the curb candidate point is determined to be valid.

If the condition is not satisfied, the controller 300 receives data from the distance sensor 100 again, extracts curb candidate points, and determines whether the condition is satisfied.

Thereafter, the control unit 300 performs view conversion by projecting the extracted curb candidate points onto the XZ plane, which is a plane parallel to the side of the curb (1250), and a plurality of points existing on both the height value of the curb candidate points and the straight line. The height values of them are extracted (1260).

The control unit 300 determines whether the height of the curb candidate point is simply increased or decreased, and determines that the curb candidate point is valid when the condition is satisfied. Further, on the condition that the heights of a plurality of points on both sides of the straight line are higher or lower than the height of the curb candidate point, when the condition is satisfied, the curb candidate point is determined to be valid (1270). If the condition is not satisfied, the controller 300 receives data from the distance sensor 100 again, extracts curb candidate points, and determines whether the condition is satisfied.

When it is determined that the curb candidate points are valid, the controller 300 determines the curb candidate points as curb points and creates a curb line using the curb points (1280).

By detecting information about the curb through such a process, it is possible to quickly and accurately detect curb information considering the geometric structure of the curb.

Here, it has been described that the control unit 300 extracts information about the curb, but as described above, it will be understood that the curb detection unit 400 included in the control unit 300 performs the above process.

Referring to FIG. 12 , the location recognition unit 500 included in the control unit 300 receives curb point and curb line information from the curb detection unit 400 (1310). The location recognition unit 500 receives map information from the storage unit 200 and extracts curb information of the map from the map information (1320). The location recognizer 500 determines the current location of the vehicle by matching the curb point with the curb information on the map (1330), and updates the current location of the vehicle (1340).

As described above, since the current location of the vehicle on the road can be recognized by comparing the detected curb point with the curb information on the map, the location of the vehicle can be recognized even when the lane is blurred or erased.

Referring to FIG. 13 , the driving path generator 600 included in the control unit 300 receives curb line and vehicle location information (1410), and determines a drivable area based on the curb line and vehicle location (1420). ). The driving path generation unit 600 creates a driving path of the vehicle within a drivable area (1430), and determines whether a risk factor exists in the driving path to determine suitability of the driving path (1440).

When there is a risk factor in the driving path, the driving path creation unit 600 determines that the driving path is unsuitable, creates an avoidance path considering the curb line, and transmits the driving path to the driving unit 700 so that the vehicle can travel along the driving path. (1450). When there are no risk factors in the driving path, the driving path generating unit 600 transmits the generated driving path to the driving unit 700 so that the vehicle can be driven along the driving path (1460).

As described above, by determining the drivable area of the vehicle and generating the driving route, it is possible to respond to an unexpected situation while driving and to promote safer driving.

Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium storing instructions executable by a computer. Instructions may be stored in the form of program codes, and when executed by a processor, create program modules to perform operations of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

Computer-readable recording media include all types of recording media in which instructions that can be decoded by a computer are stored. For example, there may be read only memory (ROM), random access memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage device, and the like.

As above, the disclosed embodiments have been described with reference to the accompanying drawings. Those skilled in the art to which the present invention pertains will understand that the present invention can be implemented in a form different from the disclosed embodiments without changing the technical spirit or essential features of the present invention. The disclosed embodiments are illustrative and should not be construed as limiting.

1: vehicle
100: distance sensor
200: storage unit
300: control unit
400: curbstone detection unit
410: data acquisition unit
420: view conversion unit
430: feature extraction unit
440: data judgment unit
500: location recognition unit
510: map information processing unit
520: data processing unit
530: position determination unit
600: path generation unit
610: drivable area determination unit
620: path generation unit
630: risk judgment unit
700: driving unit

Claims (20)

a distance sensor that collects data about the environment around the vehicle;
a storage unit that receives and stores map information;
Curb-related information is extracted using the data received from the distance sensor, the vehicle position is determined by comparing the curb-related information and the curb-stone information on the map, and driving is possible based on the curb-related information and the vehicle position. a control unit that determines an area and creates a driving route; and
A driving unit that receives the driving path generated by the control unit and drives the vehicle according to the driving path;
Information about the curb,
contains a curb candidate point, curb point or curb line;
The control unit,
Project the data received from the distance sensor onto a specific plane, extract curb candidate points from the specific plane, and determine whether the extracted curb candidate points satisfy specific conditions to generate curb points and curb lines,
Project the data as a plurality of points on a plane parallel to the ground, set two points at regular intervals as starting points to generate a straight line equation, and detect points belonging to a normal distribution based on the straight line equation to obtain curb candidate points extract,
The curb candidate point is projected onto a plane parallel to the curb side, and the curb candidate point is determined to be valid when the condition is satisfied, on the condition that the height value of the curb candidate point simply increases or decreases;
A vehicle that determines the effective curb candidate point as a curb point, and generates the curb line using the curb point. delete delete delete According to claim 1,
The control unit,
A vehicle that determines that the curb candidate point is valid if the condition is satisfied, on the condition that a plurality of points located within a certain distance from the straight line according to the straight line equation exist on both sides of the straight line. delete According to claim 1,
The control unit,
A vehicle that determines whether the curb candidate point is valid if the condition is satisfied, on the condition that the heights of a plurality of points existing on both sides of the straight line are higher or lower than the height of the curb candidate point. delete According to claim 1,
The control unit,
A vehicle that determines the current location of the vehicle by matching the curb information of the map with the curb point. According to claim 1,
The control unit,
The drivable area is determined based on the curb line and the vehicle position, a driving path of the vehicle is created within the drivable area, the suitability of the driving path is determined based on risk factors present in the driving path, and when unsuitable A vehicle that creates an avoidance path considering the curb line. Collecting data about the surrounding environment of the vehicle;
Receiving and storing map information;
Extracting information about the curb using the collected data;
determining the location of the vehicle by comparing the curb information with curb information on a map;
determining a drivable area based on the curb information and the vehicle position and generating a driving route; and
Including; driving a vehicle according to the driving route;
the information about the curb includes a curb candidate point, a curb point, or a curb line;
The step of extracting information about the curbstone,
projecting the data onto a specific plane;
extracting curb candidate points on a specific plane onto which the data is projected; and
Determining whether the extracted curb candidate points satisfy a specific condition to generate curb points and curb lines;
The step of projecting the data onto a specific plane,
Projecting the data as a plurality of points on a plane parallel to the ground;
The step of extracting the consecutive candidate points,
Setting two points at regular intervals as starting points to generate a linear equation, and extracting curb candidate points by detecting points belonging to a normal distribution based on the linear equation,
The step of projecting the data onto a specific plane,
Projecting the curb candidate points onto a plane parallel to the side of the curb;
The step of generating the curb point and curb line,
Determining that the curb candidate point is valid under the condition that the height value of the curb candidate point is simply increased or simply decreased, when the condition is satisfied;
A control method of a vehicle comprising determining the valid curb point as a curb point and generating the curb line using the curb point. delete delete delete According to claim 11,
The step of generating the curb point and curb line,
Determining that the curb candidate point is valid on the condition that a plurality of points located within a certain distance from the straight line according to the straight line equation exist on both sides of the straight line; further comprising, the vehicle control method . delete According to claim 11,
The step of generating the curb point and curb line,
Determining that the curb candidate points are valid on condition that the heights of the plurality of points on both sides of the straight line are higher or lower than the heights of the curb candidate points; method. delete According to claim 11,
Determining the location of the vehicle,
The vehicle control method further comprising determining the current location of the vehicle by matching the curb information of the map with the curb point. According to claim 11,
The step of generating the driving route is,
determining a drivable area based on the curb line and the vehicle position;
generating a travel path of the vehicle within the drivable area; and
The control method of a vehicle further comprising: determining suitability of the driving route based on risk factors present in the driving route, and generating an avoidance route in consideration of the curb line when the driving route is unsuitable.

Images