Method for Controlling Vehicle Travel and Autonomous Vehicle Using the Same

Abstract

The present invention relates to a vehicle driving control method and an autonomous vehicle using the method. The vehicle driving control method includes: calculating, by a controller, a lateral speed of an adjacent vehicle traveling in a lane adjacent to a driving lane in which the autonomous vehicle travels in a road width direction, and a longitudinal speed of the adjacent vehicle in a direction in which the adjacent lane extends; designating, by the controller, a predetermined road section based on the longitudinal speed, and calculating, within the road section and based on an assumption that the adjacent vehicle maintains an offset distance in the road width direction in the adjacent lane, a first path by the controller; and applying, by the controller, the lateral speed to the first path to calculate a second path corresponding to a predicted driving path of the adjacent vehicle.

Description

[0001] Cross - reference to related applications

[0002] This application claims the priority and benefit of Korean Patent Application No. 10 - 2018 - 0164599, filed on December 18, 2018, the entire contents of which are incorporated herein by reference. Technical field

[0003] The present invention relates to a vehicle driving control method and an autonomous vehicle using the same. Background art

[0004] The statements in this section merely provide background information related to the present invention and do not constitute prior art.

[0005] General lane - change technologies are only configured to determine whether a lane change can be made within a predetermined time when a driver shows an intention to change lanes (e.g., when the driver turns on a turn signal), and perform a lane change when it is determined that a lane change is possible.

[0006] In addition, in most research on autonomous driving, a lane change is only performed when a lane change is possible (e.g., when a collision - avoiding route is generated). Moreover, different from level 2 autonomous driving (ADAS system), level 4 autonomous driving must be designed such that it can travel from the current position to the destination without driver intervention under restricted operational design domain (ODD) conditions. Therefore, general lane - change technologies are difficult to meet the requirements of level 4 autonomous driving.

[0007] We have found that general autonomous vehicles predict the driving paths of adjacent vehicles based on the relative speeds of adjacent vehicles (which are measured by distance sensors), without considering information about driving lanes and boundary lines. Therefore, it is impossible to determine whether a lane change will occur in various road situations (e.g., intersections and curves), or accurately predict the time when a lane change will occur and the position where a lane change will occur. Therefore, it is only possible to passively respond to these situations by suddenly decelerating, rather than flexibly responding to these situations. Summary of the invention

[0008] The present invention provides an autonomous driving control method that can estimate a driving path based on the longitudinal speed and lateral speed of adjacent vehicles (i.e., vehicles traveling adjacent to the host vehicle) calculated based on a reference driving lane or road shape, so that it is possible to more accurately predict whether the driving lane of an adjacent vehicle will change, and provides a vehicle using the method.

[0009] The object of the present invention designed to solve problems is not limited to the above object, and based on the following detailed description of the present invention, those skilled in the art will clearly understand other unmentioned objects.

[0010] In one embodiment of the present invention, a vehicle driving control method includes: calculating, by a controller, a lateral speed of an adjacent vehicle traveling in a lane adjacent to a driving lane in which an autonomous vehicle is traveling in a road width direction, and a longitudinal speed of the adjacent vehicle in a direction in which the adjacent lane extends; based on the longitudinal speed, specifying, by the controller, a predetermined road section, and calculating, within the predetermined road section and based on an assumption that the adjacent vehicle maintains an offset distance in the road width direction in the adjacent lane, a first path by the controller; applying, by the controller, the lateral speed to the first path to calculate a second path corresponding to a predicted driving path of the adjacent vehicle.

[0011] The first path can be calculated based on map information including a plurality of points representing boundary lines of each of the driving lane and the adjacent lane and a center line between the boundary lines.

[0012] The vehicle driving control method can further include: tracking the second path to determine whether the second path crosses a boundary line between the driving lane and the adjacent lane, and predicting an entry point of the adjacent vehicle based on an intersection point between the second path and the boundary line.

[0013] The vehicle driving control method can further include: controlling the driving of the autonomous vehicle based on the time required for each of the autonomous vehicle and the adjacent vehicle to reach the predicted entry point.

[0014] The step of controlling the driving of the autonomous vehicle can include: accelerating the autonomous vehicle when a first arrival time of the adjacent vehicle is greater than a second arrival time of the autonomous vehicle; determining that the adjacent vehicle is a vehicle having a potential possibility of entering (hereinafter, simply referred to as "potential entering vehicle") and decelerating the autonomous vehicle when the first arrival time of the adjacent vehicle is equal to or less than the second arrival time of the autonomous vehicle.

[0015] Through the description provided herein, other application fields will become apparent. It should be understood that this specification and specific examples are only for illustrative purposes and are not intended to limit the scope of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to better understand the present invention, various embodiments of the present invention given by way of example will now be described with reference to the accompanying drawings, in which:

[0017] Figure 1Schematic block diagram showing an autonomous vehicle according to an embodiment of the present invention;

[0018] Figure 2 Schematic diagram showing a method in which a controller calculates the lateral speed and longitudinal speed of an adjacent vehicle based on a lane in an embodiment of the present invention;

[0019] Figure 3 Schematic diagram showing a method in which a controller calculates a first path based on the longitudinal speed of an adjacent vehicle in an embodiment of the present invention;

[0020] Figure 4 To show that in an embodiment of the present invention, the controller takes into account Figure 3 Schematic diagram showing a method in which the controller calculates a second path by considering the first path calculated in and the lateral speed of the adjacent vehicle;

[0021] Figure 5 To show that in another embodiment of the present invention, the controller is based on Figure 4 Schematic diagram showing a method in which the controller predicts the entry point of an adjacent vehicle based on the second path calculated in ;

[0022] Figure 6 Schematic diagram showing an application example of an autonomous vehicle in an embodiment of the present invention;

[0023] Figure 7 Schematic diagram showing an application example of an autonomous vehicle in an embodiment of the present invention when the autonomous vehicle is at an intersection; and

[0024] Figure 8 Flowchart showing a vehicle driving control method in an embodiment of the present invention.

[0025] The drawings described herein are for illustrative purposes only and are not intended to limit the scope of the present invention in any way. Detailed Description

[0026] The following description is merely exemplary in nature and is not intended to limit the invention, its application, or uses. It should be understood that throughout the drawings, corresponding reference numerals represent the same or corresponding components and features.

[0027] Since the exemplary embodiments of the present invention can be variously modified and can have various embodiments, it should be understood that the present invention includes all changes, equivalents, and alternative forms that fall within the spirit and scope of the present invention.

[0028] It should be understood that although terms such as "first" and "second" may be used herein to describe various elements, the corresponding elements should not be understood as being limited by these terms. These terms are only used to distinguish one element from another. Additionally, terms specifically defined in consideration of the construction and operation of the embodiments are for explaining the exemplary embodiments and not for limiting the scope of the present invention.

[0029] The terms used in this specification are only for explaining the specific embodiments and are not intended to limit the present invention. The singular forms may include the plural forms unless it is clearly different in the context. It will also be understood that when terms such as "comprising", "having", etc. are used in this specification, it indicates the presence of the described features, values, steps, operations, elements, components, or combinations thereof, but does not exclude the presence or addition of one or more other features, values, steps, operations, elements, components, and / or combinations thereof.

[0030] Unless otherwise defined, all terms including technical and scientific terms used in this specification have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention pertains. It should be further understood that terms defined, for example, in common dictionaries should be understood as having meanings consistent with their meanings in the relevant field and the context of the present invention, and are not to be understood in an idealized or overly formal sense unless clearly so defined herein.

[0031] Figure 1 A schematic block diagram showing an autonomous vehicle according to an embodiment of the present invention.

[0032] As Figure 1 shown, the autonomous vehicle represented by reference numeral 10 may include a global positioning system (GPS) receiving unit 100, a sensor unit 200, a map storage unit 300, a controller 400, and a driving unit 500.

[0033] Here, terms such as "unit", "controller", or "module" should be understood as units that process at least one function or operation and can be implemented in a hardware manner (e.g., a processor), a software manner, or a combination of a hardware manner and a software manner.

[0034] The GPS receiving unit 100 can measure the current position of the autonomous vehicle 10 by using the signals transmitted from GPS satellites. The GPS receiving unit 100 calculates the distance between the satellite and the GPS receiving unit 100 by using the time difference between the time when the satellite transmits the signal and the time when the GPS receiving unit 100 receives the signal. The GPS receiving unit 100 calculates the current position of the autonomous vehicle 10 by using the calculated distance between the satellite and the GPS receiving unit 100 and the information about the satellite position included in the transmitted signal. At this time, the GPS receiving unit 100 can use the triangulation method to calculate the current position of the autonomous vehicle 10.

[0035] The sensor unit 200 can acquire information about the driving state of the autonomous vehicle 10 and information about the driving states of at least one adjacent vehicle 20 driving in a lane adjacent to the driving lane of the autonomous vehicle 10. To acquire the driving state information of the autonomous vehicle 10 and the adjacent vehicle 20, the sensor unit 200 may include an out-vehicle information sensor 210 and an in-vehicle information sensor 230.

[0036] The out-vehicle information sensor 210 may include a camera sensor 211 and a distance sensor 213; the camera sensor 211 is used to acquire information about the image around the photographed autonomous vehicle 10; the distance sensor 213 is used to acquire information about the distance between the autonomous vehicle 10 and an object located near the autonomous vehicle 10. The distance sensor 213 may be implemented as a LIDAR sensor or a RADAR sensor. The out-vehicle information sensor 210 (hereinafter, referred to as the "first sensor" for convenience of description) may collect out-vehicle information, for example, the relative position, relative speed, and direction information of the adjacent vehicle 20 located within a predetermined detection range FR.

[0037] The camera sensor 211 can acquire information about the image around the autonomous vehicle 10 through an image sensor, and can perform image processing (for example, noise removal) on the acquired image.

[0038] The distance sensor 213 can measure the arrival time of a laser pulse or an electromagnetic wave emitted toward the adjacent vehicle 20 to calculate the distance between the autonomous vehicle 10 and the adjacent vehicle 20.

[0039] The in-vehicle information sensor 230 (hereinafter, referred to as the "second sensor" for convenience of description) may include a speed sensor 231, an acceleration sensor 233, a yaw rate sensor 235, and a steering angle sensor 237, and the in-vehicle information sensor 230 can measure in-vehicle information, for example, the absolute speed, acceleration, yaw rate, and steering angle of the autonomous vehicle 10.

[0040] The map storage unit 300 may store information about a high-definition map (from which lanes can be distinguished) in the form of a database (DB). The high-definition map may be automatically and periodically updated via wireless communication or may be updated manually by a user.

[0041] The map storage unit 300 may provide road shape data representing the shape of a specific section of a road including the road position in the form of a coordinate train. Here, to represent the shape of the road, the road shape data shows the boundary line Q and the boundary line S on both sides of the road and the center line R between the boundary line Q and the boundary line S as a set of points, and shows the longitudinal data and the lateral data of each point as coordinate values. In addition, the road shape data may provide information about the intercept orientation at each point, that is, information about the direction of the straight line tangent to the curve of the road at each point. Here, assuming that the absolute direction of the due north direction is 0°, the intercept direction information is shown in the range of 0° to 360° in the clockwise direction.

[0042] The controller 400 may identify the absolute position of the adjacent vehicle 20 based on the current position of the autonomous vehicle 10 received from the GPS receiving unit 100 and the external information and internal information of the autonomous vehicle 10 received from the sensor unit 200. Here, the adjacent vehicle 20 is a vehicle traveling in a lane adjacent to the traveling lane of the autonomous vehicle 10.

[0043] The controller 400 may match the current position of the autonomous vehicle 10 and the absolute position of the adjacent vehicle 20 to the high-definition map with reference to the road shape data, and may calculate the lateral speed of the adjacent vehicle 20 in the road width direction Y' and the longitudinal speed of the adjacent vehicle 20 in the direction X' in which the adjacent lane extends.

[0044] The controller 400 may specify a road section L (which is shown as a set of points) based on the longitudinal speed of the adjacent vehicle 20, and may calculate a first path by assuming that the adjacent vehicle 20 maintains an offset in the road width direction Y' in the adjacent lane. Here, the specified road section L (which is a distance preset by the user) represents the distance in the lane extension direction (i.e., the longitudinal direction X').

[0045] The controller 400 may apply the lateral speed of the adjacent vehicle 20 to the first path to calculate a second path corresponding to the predicted traveling path of the adjacent vehicle 20, and may predict an interruption point (hereinafter, referred to as the "incoming" point for convenience) at which the adjacent vehicle 20 attempts to enter the boundary line S between the traveling lane and the adjacent lane based on the second path.

[0046] The controller 400 may calculate the time to collision (TTC) required for each of the autonomous vehicle 10 and the adjacent vehicle 20 to reach a predicted entry point, and may send a signal for controlling the driving of the autonomous vehicle 10 to the driving unit 500. Here, the control signal sent by the controller 400 may include a signal for controlling the speed of the autonomous vehicle 10 such that at least one of deceleration, acceleration, or speed maintenance is performed.

[0047] The driving unit 500 is configured to drive the autonomous vehicle 10 in response to the control signal sent by the controller 400, and the driving unit 500 may include components for actually driving the vehicle, such as a brake, an accelerator, a transmission, and a steering device. For example, in the case where the control signal from the controller 400 is a signal indicating deceleration, the brake of the driving unit 500 may perform a deceleration operation.

[0048] Hereinafter, Figure 2 a method for calculating the lateral speed of the adjacent vehicle 20 in the road width direction Y' and the longitudinal speed of the adjacent vehicle 20 in the direction X' in which the adjacent lane extends will be described.

[0049] Figure 2 A schematic diagram showing a method in which a controller calculates the lateral speed and longitudinal speed of an adjacent vehicle based on a lane in an embodiment of the present invention.

[0050] Referring to Figure 2 , the controller 400 may match the current position of the autonomous vehicle 10 and the absolute position of the adjacent vehicle 20 to a high-definition map with reference to road shape data, and may calculate the absolute speed, absolute position, or direction information of the adjacent vehicle 20 traveling in the adjacent lane by using the external information and internal information of the autonomous vehicle 10 collected from the sensor unit 200.

[0051] For example, the controller 400 may calculate the absolute speed, absolute position, or direction information of the adjacent vehicle 20 in consideration of the relative speed and relative distance of the adjacent vehicle collected by the first sensor 210 and the absolute speed or steering angle of the autonomous vehicle 10 measured by the second sensor 230. Here, the direction information represents the absolute direction in the direction in which the adjacent vehicle 20 advances, and the absolute direction represents the heading angle θ of the adjacent vehicle 20 moving in the clockwise direction based on the north. β .

[0052] The controller 400 may extract the boundary line S adjacent to the adjacent vehicle 20 matched on the high-definition map, and may calculate the lateral speed of the adjacent vehicle 20 in the road width direction Y' by using triangulation and the longitudinal speed of the adjacent vehicle 20 in the direction X' in which the adjacent lane extends

[0053] As shown Figure 2 in the figure, the controller 400 may extract a second node N2 located at the shortest distance from the first node N1 (hereinafter referred to as the "first node N1") based on the center of gravity of the adjacent vehicle 20 from a set of points on the adjacent boundary line S. In addition, the controller 400 may calculate the intersection point of an imaginary line extending in the advancing direction of the adjacent vehicle 20 from the first node N1 and a line tangent to the adjacent boundary line S at the second node N2 (hereinafter referred to as the "third node N3"). The first node to the third node N1, N2, and N3 may be displayed as coordinate values including longitudinal data and lateral data.

[0054] At this time, the direction vector between the first node N1 and the second node N2 represents the relative movement direction of the adjacent vehicle 20 in the road width direction Y', and the direction vector between the second node N2 and the third node N3 represents the relative movement direction of the adjacent vehicle 20 in the direction in which the adjacent lane extends. In addition, the lateral speed (which will be described subsequently) of the adjacent vehicle 20 may be defined as the traveling speed of the adjacent vehicle 20 in the road width direction Y', and the longitudinal speed of the adjacent vehicle 20 may be defined as the traveling speed of the adjacent vehicle 20 in the direction X' in which the adjacent lane extends.

[0055] The controller 400 may calculate the lateral speed and the longitudinal speed of the adjacent vehicle 20 based on the absolute speed of the adjacent vehicle 20 and the linear distances between the first node and the third node N1, N2, and N3.

[0056] [Equation 1]

[0057]

[0058] Here, Lv is the linear distance between the first node and the third node, Ly is the linear distance between the first node and the second node, Lx is the linear distance between the second node and the third node, and is the absolute speed of the adjacent vehicle.

[0059] In addition, the controller 400 may calculate the lateral speed and the longitudinal speed of the adjacent vehicle 20 based on the absolute speed of the adjacent vehicle 20 and predetermined direction information. α In another example, Equation 2 may be used. Here, the predetermined direction information includes information about the intercept direction θ βinformation.

[0060] [Equation 2]

[0061]

[0062]

[0063] Here, is the absolute speed of the adjacent vehicle, θ α is the intercept direction of the second node, and θ β is the heading angle of the adjacent vehicle.

[0064] Hereinafter, reference will be made to Figure 3 to describe a method for the controller to calculate a first path corresponding to the longitudinal driving path of the adjacent vehicle 20.

[0065] Figure 3 A schematic diagram showing a method for the controller to calculate a first path based on the longitudinal speed of an adjacent vehicle in an embodiment of the present invention.

[0066] Referring to Figure 3 , the controller 400 can calculate the first path by assuming that the adjacent vehicle 20 traveling in an adjacent lane adjacent to the driving lane of the autonomous vehicle 10 maintains an offset in the road width direction Y' in the adjacent lane and referring to the high-definition map information

[0067] The controller 400 can receive map shape data from the map storage unit 300, and the map shape data shows the boundary lines Q and S of each of the driving lane and the adjacent lane and the center line R between the boundary line Q and the boundary line S as a set of points.

[0068] The controller 400 can approximate the point corresponding to the absolute position of the adjacent vehicle 20 matched on the high-definition map as the reference node O0 of the adjacent vehicle 20, and can calculate the offset distance d of the reference node O0 based on the center line of the adjacent lane road .

[0069] Here, the offset distance d road is the distance that the reference node O0 of the adjacent vehicle 20 moves right or left from the center line of the adjacent lane in a direction perpendicular to the extension direction of the adjacent lane (hereinafter, for convenience, it is referred to as the "road width direction"), and can satisfy 0 ≤ d road ≤ L QS / 2 (where L QS is the distance between the boundary lines of the adjacent lane).

[0070] In addition, the controller 400 can extract the reference node R0 of the center line R that is at the shortest distance from the reference node O0 of the center line R among a set of points on the center line R from the adjacent vehicle 20, and can calculate the node sequence vector information about the center line R in consideration of the longitudinal speed of the adjacent vehicle 20 and a predetermined time period t

[0071] At this time, each node R0, R1,... and R of the center line R can be defined by Equation 3 k The longitudinal movement distance between

[0072] [Equation 3]

[0073]

[0074] Here is the node R i-1 and the node R i The longitudinal movement distance between (where i is an integer of 1 or greater), is the longitudinal speed of the adjacent vehicle 20, Δt i is from the node R i-1 Moving to the node R i The time required. At this time, Δt i can be a time preset by the user as a predetermined time period, and the node sequence vector information about the center line R can provide equally spaced road shape data.

[0075] Meanwhile, the controller 400 can predict the entry point of the adjacent vehicle 20 in units of a predetermined road section L. The reason is that it is desired to effectively predict the entry point of the adjacent vehicle 20 within the limited data processing capacity of the controller 400. Here, the predetermined road section L is the longitudinal distance preset by the user in the direction X' of the extension of the adjacent lane.

[0076] The controller 400 can specify the predetermined road section L based on the node sequence vector information about the center line R At this time, the controller 400 can calculate k that satisfies Equation 4 and the node R at the end of the road section L between the node R k-1 and the node R k n and can extract the node sequence vector information about the center line R within the road section L

[0077] [Equation 4]

[0078]

[0079] ​Here, k is an integer of 1 or greater, and n satisfies k-1. <n<k,并且 is node R n With node R k-1 The vertical distance between.

[0080] In addition, the controller 400 may assume that the adjacent vehicle 20 maintains an offset distance d in the road width direction Y′ in the adjacent lane. road Taking into account the extracted node sequence vector information about the center line R The first path is calculated using Equation 5

[0081] [Equation 5]

[0082]

[0083] Here, d road is the offset distance relative to the center line R, is the offset direction vector, is the information about each node sequence vector of the center line R, and the offset direction vector are nodes R0, R1, ..., R on the center line R in the road width direction Y'. k-1 and R n The unit vector at each node of .

[0084] First Path The node sequence vector information about the longitudinal travel path of the adjacent vehicle 20 in the predetermined road section L is included. And the first path Each node O0, O1, ..., O k-1 and O n The nodes R0, R1, ..., R of the center line R can be k-1 and R n The corresponding node in the road is offset by a distance d in the road width direction. road However, at an offset distance d road When it is 0, the first path Can correspond to the node sequence vector information about the center line R

[0085] In the following, reference will be made to Figure 4 A method by which the controller calculates a second path corresponding to the predicted travel path of the neighboring vehicle 20 is described.

[0086] Figure 4 To illustrate, in one embodiment of the present invention, the controller takes into account Figure 3Schematic diagram of a method for calculating a second path based on a first path calculated in FIG.

[0087] refer to Figure 4 , the controller 400 can refer to the high-definition map information to calculate the lateral speed of the adjacent vehicle 20 Apply to the first path (The first path corresponds to the longitudinal travel path of the adjacent vehicle 20) to calculate the second path (The second path corresponds to the predicted travel path of the adjacent vehicle 20).

[0088] The controller 400 can calculate the adjacent vehicle 20 in the road width direction Y' on the first path Each node O0, O1, ..., O k-1 and O n The lateral movement distance d path_i , and the node sequence vector information about the longitudinal travel path of the adjacent vehicle 20 can be taken into account The lateral movement distance d of the adjacent vehicle 20 path_i and the heading vector of the adjacent vehicle 20 To calculate the node sequence vector information including the predicted driving path of the adjacent vehicle 20 The second path Here, the first path The node O0 and the second path The node P0 includes longitudinal data and lateral data having the same coordinate values.

[0089] The lateral speed of the adjacent vehicle 20 can be Applied to the adjacent vehicle 20 from node O i Move to node P i The time required t i To calculate the lateral movement distance d path_i , and the lateral movement distance d can be defined by Equation 6 path_i .

[0090] [Equation 6]

[0091]

[0092] Here, the adjacent vehicle 20 is located in the lateral direction from the node O. i Move to node P i The time required t i The adjacent vehicle 20 moves from the node O0 to the node O in the longitudinal direction. i The time required t i The same, and the time t can be calculated using Equation 7 i .

[0093] [Equation 7]

[0094]

[0095] Here, t x is the time required for the adjacent vehicle 20 to move from the node O x to the node P x in the lateral direction, and t n is the time required for the adjacent vehicle 20 to move from the node O n which is located at the end of the road section L n to the node P i in the lateral direction. Δt i-1 is the time required for the adjacent vehicle 20 to move from O i-1 (or the node R i ) to the node O i (or the node R ), and v

[0096] is the longitudinal speed of the adjacent vehicle 20. The forward direction vector of the adjacent vehicle 20 is a unit vector in the road width direction with respect to the forward direction of the adjacent vehicle 20. At this time, the forward direction vector of the adjacent vehicle 20 may have the same scalar as the above offset direction vector , and the directions of the two vectors may be the same or opposite. For example, the forward direction vector of the adjacent vehicle 20 and the offset direction vector may satisfy the correlation

[0097] where "+" indicates the same direction and "-" indicates the opposite direction. The lateral movement distance d path_i of the adjacent vehicle 20 and the forward direction vector of the adjacent vehicle 20 to calculate a second path corresponding to the predicted driving path of the adjacent vehicle 20

[0098] [Equation 8]

[0099]

[0100] Here, is the first path, which includes the node sequence vector information regarding the longitudinal driving path of the adjacent vehicle 20, and d path_iis the lateral movement distance from node O i to node P i is the lateral movement distance, is the forward direction vector of the adjacent vehicle 20, d road is the offset distance relative to the center line R, and is the information of each node sequence vector with respect to the center line R. Equation 8 can be derived by referring to Equation 5 and the correlation above.

[0101] Hereinafter, a method will be described with reference to Figure 5 which predicts the entry point where the adjacent vehicle 20 attempts to enter the boundary line between the driving lane and the adjacent lane based on the second path, and calculates the time required for each of the autonomous vehicle 10 and the adjacent vehicle 20 to reach the predicted entry point.

[0102] Figure 5 To illustrate, in another embodiment of the present invention, a schematic diagram of a method in which the controller predicts the entry point of the adjacent vehicle based on the second path Figure 4 calculated in is shown.

[0103] Referring to Figure 5 , the controller 400 can predict the entry point where the adjacent vehicle attempts to enter the boundary line S between the driving lane and the adjacent lane based on the second path .

[0104] The controller 400 can extract the coordinates of the feature point P0' of the adjacent vehicle 20 in consideration of the out-of-vehicle information acquired by the first sensor 210 (for example, information about the overall width and overall length of the adjacent vehicle 20), and can convert the reference node O0 of the adjacent vehicle 20 into the feature point coordinates P0'. In addition, the controller 400 can translate the second path parallelly based on the coordinates of the converted feature point P0'. Here, the feature point P0' may include the corner regions 1, 2, 3, and 4 of the adjacent vehicle 20, and there is a high possibility that the autonomous vehicle 10 collides with these corner regions.

[0105] The controller 400 can calculate at least one intersection point P between the at least one translated second path and the boundary line S between the driving lane of the autonomous vehicle and the adjacent lane by referring to the high-definition map information cut-in , and can predict this intersection point P cut-in as the entry point P cut-in of the adjacent vehicle 20.

[0106] The controller 400 can obtain from the at least one translated second path The nodes P0', P1',..., and P n ' are extracted to obtain the nodes P i ' located in the adjacent lane and the nodes P i+1 ' located in the driving lane in a state adjacent to the boundary line S.

[0107] The controller 400 can calculate the first time t i required for the adjacent vehicle 20 to reach the predicted entry point P i+1 ' based on the nodes P cut-in ' adjacent to the boundary line S, the nodes P cut-in ', and the entry point P cut-in . The first time t cut-in can be defined by Equation 9.

[0108] [Equation 9]

[0109]

[0110] Here, is the distance between the node P i and the intersection point P cut-in . is the distance between the node P i and the node P i+1 . t i is the time required for the adjacent vehicle 20 to move to the node P i , and t i+1 is the time required for the adjacent vehicle 20 to move to the node P i+1 . At this time, t i (or t i+1 ) can be equal to the time required for the adjacent vehicle 20 to move from the node O i (or the node O i+1 ) to the node P i (or the node P i+1 ) in the lateral direction (which is calculated by Equation 7 above).

[0111] The controller 400 can calculate the second time t ego required for the autonomous vehicle 10 to reach the predicted entry point P cut-in based on the absolute speed V ego of the autonomous vehicle 10 obtained by the second sensor 230. The second time t ego can be defined by Equation 10.

[0112] [Equation 10]

[0113]

[0114] Here, is the current position P of the autonomous vehicle 10 ego from the intersection point P cut-in and V ego is the absolute speed V of the autonomous vehicle 10 ego .

[0115] The controller 400 may mutually compare the calculated first time t cut-in with the calculated second time t ego to predict whether a collision will occur between the autonomous vehicle 10 and the adjacent vehicle 20, and may send a signal for driving the autonomous vehicle 10 to the driving unit 500.

[0116] At the first time t cut-in equal to or greater than the second time t ego the controller 400 may perform control to increase or maintain the speed of the autonomous vehicle 10 to avoid a collision with the adjacent vehicle 20.

[0117] At the first time t cut-in less than the second time t ego the controller 400 may determine that the adjacent vehicle 20 is a potential incoming vehicle, and may perform control to decelerate the autonomous vehicle 10.

[0118] As described above, the autonomous vehicle 10 according to an exemplary embodiment of the present invention can accurately predict the driving path of the adjacent vehicle 20 based on high-definition map information, and establish a driving strategy of the autonomous vehicle in advance based on the predicted driving path, thereby improving the driving stability of the autonomous vehicle.

[0119] In addition, the autonomous vehicle 10 according to an embodiment of the present invention can predict the driving path of the adjacent vehicle 20 based on the longitudinal speed and lateral speed of the adjacent vehicle 20 calculated based on the road shape data on the reference driving lane or the adjacent lane, thereby accurately determining the intention of the adjacent vehicle 20 to enter on a straight road and / or a curved road, and pre-calculating the entry point of the adjacent vehicle 20. Therefore, stable deceleration or acceleration control can be performed.

[0120] Meanwhile, the autonomous vehicle 10 according to a previous embodiment of the present invention can be applied to Figure 6 and Figure 7 the various driving conditions shown in. This will be described below with reference to Figure 6 and Figure 7 .

[0121] Figure 6 is a schematic diagram showing an application example of an autonomous vehicle according to an embodiment of the present invention.

[0122] Figure 6 In (a) of , it is a schematic diagram showing the driving conditions where adjacent vehicles 20 simultaneously attempt to drive into the lane that the autonomous vehicle attempts to enter on a curved road.

[0123] Reference Figure 6 Referring to (a) of , when adjacent vehicle 20 attempts to drive into the lane that autonomous vehicle 10 attempts to enter on a curved road, autonomous vehicle 10 can predict the entry point of adjacent vehicle 20 and can establish a strategy for avoiding collision with adjacent vehicle 20.

[0124] Figure 6 In (b) of , it is a schematic diagram showing the driving conditions where an adjacent vehicle 20 in the reverse lane attempts to make a U-turn and enter the driving lane of the autonomous vehicle.

[0125] Reference Figure 6 Referring to (b) of , when an adjacent vehicle 20 in the reverse lane on a straight road attempts to make a U-turn and enter the driving lane of the autonomous vehicle, autonomous vehicle 10 can predict the entry point of adjacent vehicle 20 and can establish a strategy for avoiding collision with adjacent vehicle 20.

[0126] When the adjacent vehicle 20 in the reverse lane is sensed by the first sensor 210, the controller 400 can predict the driving path of the adjacent vehicle 20 or whether the adjacent vehicle 20 will drive in based on the lateral speed and longitudinal speed of the adjacent vehicle 20 in the adjacent lane, and can establish a flexible driving strategy according to the driving conditions of the adjacent vehicle 20. For example, the controller 400 can calculate the time to collision TTC required for each of the autonomous vehicle 10 and the adjacent vehicle 20 to reach the predicted entry point, and can preset a specific control signal for decelerating or accelerating the autonomous vehicle 10.

[0127] Figure 6 In (c) of , it is a schematic diagram showing the driving conditions where there are a leading vehicle and another leading vehicle in front of the autonomous vehicle in the driving lane.

[0128] Reference Figure 6 Referring to (c) of , when there are a leading vehicle 20 and another leading vehicle 30 in front of the autonomous vehicle 10 in the driving lane, the autonomous vehicle 10 according to an embodiment of the present invention can predict the departure point of the leading vehicle 20 and can establish a strategy for avoiding collision with the other leading vehicle 30.

[0129] When the front vehicle 20 in the driving lane in front of the autonomous vehicle 10 is sensed by the first sensor 210, the controller 400 may calculate the lateral speed of the front vehicle 20 in the driving lane in the road width direction and the longitudinal speed of the front vehicle 20 in the direction in which the driving lane extends, and may predict the departure point of the front vehicle 20 in the same manner as the method described with reference to Figures 3 to 5 The departure point of the front vehicle 20 is predicted in the same manner as the method described above. Here, except for predicting the departure point or the entry point according to whether the front vehicle 20 is in the driving lane of the autonomous vehicle or in an adjacent lane, the method of predicting the departure point is basically the same as the method of predicting the entry point. Therefore, its repeated description will be omitted.

[0130] The controller may predict the driving path of the front vehicle 20 in the driving lane or whether the front vehicle 20 will depart based on the lateral speed and longitudinal speed of the front vehicle 20 in the driving lane, and may establish a flexible driving strategy according to the driving condition of another front vehicle 30 obtained by the first sensor 210. For example, the controller 400 may preset a specific control signal for decelerating or accelerating the autonomous vehicle 10 based on the relative speed of another front vehicle 30.

[0131] Figure 7 FIG. is a schematic diagram showing an application example of an autonomous vehicle in an embodiment of the present invention when the autonomous vehicle is at an intersection.

[0132] Figure 7 In FIGS. (a) and (b), it is a schematic diagram showing a situation where an adjacent vehicle 20 attempts to enter the driving lane of the autonomous vehicle 10 that is going straight forward or turning left when turning right at an intersection.

[0133] As described above, when the adjacent vehicle 20 turning right at the intersection is sensed by the first sensor 210, the controller 400 may predict the driving path of the adjacent vehicle 20 or whether the adjacent vehicle 20 will enter based on the lateral speed and longitudinal speed of the adjacent vehicle 20 in the adjacent lane, and may establish a flexible driving strategy according to the driving condition of the adjacent vehicle 20. For example, the controller 400 may calculate the time to collision TTC required for each of the autonomous vehicle 10 and the adjacent vehicle 20 to reach the predicted entry point, and may preset a specific control signal for decelerating or accelerating the autonomous vehicle 10, or a specific control signal for applying torque in a direction to avoid collision with the adjacent vehicle 20 (for example, in the left direction).

[0134] Figure 7 In FIGS. (c) and (d), it is a schematic diagram showing a situation where an adjacent vehicle entering the intersection (going straight forward or turning left) attempts to enter the driving lane of the autonomous vehicle turning right at the intersection.

[0135] As described above, when the adjacent vehicle 20 entering the intersection (going straight ahead or turning left) is sensed by the first sensor 210, the controller 400 may predict the driving path of the adjacent vehicle 20 or whether the adjacent vehicle 20 will enter based on the lateral speed and longitudinal speed of the adjacent vehicle 20 in the adjacent lane, and may establish a flexible driving strategy according to the driving condition of the adjacent vehicle 20. For example, the controller 400 may calculate the time to collision (TTC) required for each of the autonomous vehicle 10 and the adjacent vehicle 20 to reach the predicted entry point, and may preset a specific control signal for decelerating or accelerating the autonomous vehicle 10.

[0136] Figure 8 A flowchart showing a vehicle driving control method in an embodiment of the present invention.

[0137] Reference Figure 8 , the controller 400 may obtain information on the driving states of the autonomous vehicle and the adjacent vehicle through the GPS receiving unit 100, the sensor unit 200, and the map storage unit 300 (S801).

[0138] In step S801, the controller 400 may calculate the relative position, relative speed, and relative acceleration of the adjacent vehicle based on at least one of the image information or distance information received from the out-of-vehicle information sensor 210. Additionally, the controller 400 may further calculate the absolute position, absolute speed, and absolute acceleration of the adjacent vehicle in consideration of at least one of the position information or vehicle information of the autonomous vehicle received from the GPS receiving unit 100 and the in-vehicle information sensor 230.

[0139] Subsequently, the controller 400 may match the current position of the autonomous vehicle and the absolute position of the adjacent vehicle to the high-definition map with reference to the road shape data obtained through the map storage unit 300, and may determine the adjacent lane in which the adjacent vehicle travels to calculate the lateral speed of the adjacent vehicle 20 in the road width direction and the longitudinal speed of the adjacent vehicle 20 in the direction in which the adjacent lane extends (S802).

[0140] The controller 400 may specify a road section L (which is shown as a set of points) based on the longitudinal speed of the adjacent vehicle and may calculate a first path by assuming that the adjacent vehicle maintains an offset in the road width direction in the adjacent lane (S803). Here, the road section L to be specified (which is a user-preset distance) represents the longitudinal distance in the lane extension direction.

[0141] The controller 400 may consider the first path Lateral movement distance d of adjacent vehicle path_i and the forward direction vector of the adjacent vehicle to calculate a second path corresponding to the predicted travel path of the adjacent vehicle (S804). Here, the lateral speed of the adjacent vehicle can be used to calculate the lateral movement distance d by applying it to the time required for the adjacent vehicle to move from the first path to the second path path_i , and the forward direction vector of the adjacent vehicle can be defined as the unit vector of the adjacent vehicle in the road width direction with respect to the forward direction of the adjacent vehicle

[0142] The controller 400 can refer to the high-definition map information to determine whether the second path corresponding to the predicted travel path of the adjacent vehicle calculated in step S804 intersects the boundary line S between the driving lane and the adjacent lane (S805).

[0143] When it is determined that there is no intersection point between the second path and the boundary line S ("No" in S805), the process can return to step S801

[0144] When it is determined that there is an intersection point between the second path and the boundary line S ("Yes" in S805), the controller 400 can predict this intersection point as the entry point P of the adjacent vehicle cut-in (S806).

[0145] Subsequently, the controller 400 can compare the time to collision (TTC) required for the autonomous vehicle 10 to reach the predicted entry point with the TTC required for the adjacent vehicle 20 to reach the predicted entry point, and can send a signal for controlling the drive of the autonomous vehicle to the drive unit 500 (S807).

[0146] When the first time t cut-in required for the adjacent vehicle to reach the predicted entry point P cut-in is equal to or greater than the second time t cut-in required for the autonomous vehicle to reach the predicted entry point P ego ("No" in S807), the controller 400 can identify that the adjacent vehicle is not entering, and can execute control to increase or maintain the speed of the autonomous vehicle to avoid collision with the adjacent vehicle (S808).

[0147] When the first time t cut-in is shorter than the second time t egoIn the case of being short ( "Yes" in S807), the controller 400 may determine that the adjacent vehicle is a potential incoming vehicle, and may perform control to decelerate the autonomous vehicle (S809).

[0148] The vehicle driving control method according to the above-described embodiments of the present invention may be implemented as a program executable by a computer and stored in a computer-readable recording medium. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0149] The computer-readable recording medium may be distributed to computer systems connected through a network, and the computer-readable code thereon may be stored and executed in a distributed manner. Functional programs, codes, and code segments for implementing the above method can be easily inferred by a programmer in the field of at least one embodiment.

[0150] Although only several embodiments are described above, various other embodiments may be provided. The above embodiments may be combined in various ways unless they are incompatible, and new embodiments may be implemented thereby.

[0151] It is obvious from the above description that according to at least one embodiment of the present invention, the driving path can be estimated based on the longitudinal speed and lateral speed of adjacent vehicles calculated based on the reference driving lane or road shape, so that it is possible to more accurately predict whether the driving lane of the adjacent vehicle will change, and thus flexibly respond to various road conditions.

[0152] Therefore, it is possible to avoid hindering the traffic flow due to indiscriminate deceleration in the case of autonomous driving, and to reduce the discomfort of drivers and passengers in adjacent vehicles.

[0153] Those skilled in the art should understand that the effects achievable by the present invention are not limited to the specific contents described above, and other effects of the present invention will be more clearly understood through the above detailed description.

[0154] It is obvious to those skilled in the art that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention. Therefore, the above detailed description should not be construed as limiting the present invention in any way, but by way of example. The scope of the present invention should be determined by a reasonable interpretation of the appended claims, and all equivalent modifications made without departing from the scope of the present invention should be understood to be included within the scope of the appended claims.

Claims

1. A vehicle driving control method, comprising: Calculating, by a controller, a lateral speed of an adjacent vehicle traveling in a lane adjacent to a driving lane in which an autonomous vehicle is traveling in a road width direction, and a longitudinal speed of the adjacent vehicle in a direction in which the adjacent lane extends; Specifying, by the controller, a predetermined road section based on the longitudinal speed, and calculating, within the predetermined road section and based on an assumption that the adjacent vehicle maintains an offset distance in the road width direction in the adjacent lane, a first path by the controller; Applying, by the controller, the lateral speed to the first path to calculate a second path corresponding to a predicted driving path of the adjacent vehicle; Tracking the second path to determine whether the second path crosses a boundary line between the driving lane and the adjacent lane; Predicting an entry point of the adjacent vehicle based on an intersection point between the second path and the boundary line; Controlling the driving of the autonomous vehicle based on the time required for each of the autonomous vehicle and the adjacent vehicle to reach the predicted entry point.

2. The vehicle driving control method according to claim 1, wherein, Calculating the first path based on map information, the map information including a plurality of points representing boundary lines of each of the driving lane and the adjacent lane and a center line between the boundary lines.

3. The vehicle driving control method according to claim 1, wherein, Controlling the driving of the autonomous vehicle includes: Accelerating the autonomous vehicle when a first arrival time of the adjacent vehicle is greater than a second arrival time of the autonomous vehicle; Determining that the adjacent vehicle is a potential entry vehicle and decelerating the autonomous vehicle when the first arrival time of the adjacent vehicle is equal to or less than the second arrival time of the autonomous vehicle.

4. An autonomous vehicle, comprising: A sensor configured to acquire driving state information of the autonomous vehicle and driving state information of an adjacent vehicle traveling in a lane adjacent to a driving lane in which the autonomous vehicle is traveling; A map storage device configured to provide map information, the map information including a plurality of points representing boundary lines of each of the driving lane and the adjacent lane and a center line between the boundary lines; And A controller configured to calculate a lateral speed of the adjacent vehicle in the road width direction and a longitudinal speed of the adjacent vehicle in a direction in which the adjacent lane extends with reference to the driving state information and the map information; Wherein, the controller is configured to: Specify a predetermined road section based on the longitudinal speed; Calculate a first path within the predetermined road section and based on an assumption that the adjacent vehicle maintains an offset distance in the road width direction in the adjacent lane; Apply the lateral speed to the first path; Calculate a second path corresponding to a predicted driving path of the adjacent vehicle; Track the second path and determine whether the second path crosses a boundary line between the driving lane and the adjacent lane; Predict an entry point of the adjacent vehicle based on an intersection point between the second path and the boundary line; Control the driving of the autonomous vehicle based on the time required for each of the autonomous vehicle and the adjacent vehicle to reach the predicted entry point.

5. The autonomous vehicle according to claim 4, wherein, The controller is configured to: Execute acceleration of the autonomous vehicle when a first arrival time of the adjacent vehicle is greater than a second arrival time of the autonomous vehicle; When the first arrival time of an adjacent vehicle is equal to or less than the second arrival time of the autonomous vehicle, it is determined that the adjacent vehicle is a potential incoming vehicle, and the autonomous vehicle is decelerated.

Images