DEVICE FOR CONTROLLING A VEHICLE AND METHOD THEREOF

Abstract

A device for controlling a vehicle is presented. The device is configured to generate and correct lane boundaries based on objects detected by a sensor and map information associated with a global positioning system when it is difficult to determine lane boundaries due to occlusions and disappearance of boundary objects.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to an apparatus and a vehicle control method, and more particularly relates to a technology using Light Detection and Ranging (LiDAR). BACKGROUND

[0002] Various studies are conducted to identify or detect an external object using different sensors to assist a host vehicle in driving.

[0003] In particular, the external object may be detected using a sensor (e.g., LiDAR) while the host vehicle is driving in a driver assistance device activation mode or in an autonomous driving or propulsion mode.

[0004] There is a need to accurately detect the area within which the host vehicle can travel by detecting a road edge using a sensor (e.g., LiDAR). Especially when the road edge is obscured by an external object (e.g., an external vehicle), problems may arise (e.g., the road edge disappears). SUMMARY

[0005] According to the present disclosure, an apparatus comprises a sensor, a communication circuit, and a processor, wherein the processor is configured to determine a first reference point within a line segment corresponding to a rear side of an external vehicle, the line segment being one of line segments forming a first virtual box corresponding to the external vehicle detected by the sensor, to remove points from a plurality of points obtained by the sensor, based on tracking the first reference point in areas divided by grids associated with frames of a particular section, relative to at least one of a second reference point located within a second line segment corresponding to a rear side of a first stationary object, the second line segment being one of line segments,which form a second virtual box corresponding to the first stationary object, or a third reference point located within a third line segment corresponding to a back side of a second stationary object, the third line segment being one of line segments forming a third virtual box corresponding to the second stationary object, the points being arranged in an area different from an area where a host vehicle is present, to correct an error with respect to a location or position of the host vehicle by comparing a first position of the host vehicle included in map information received via the communication circuit and a second position of the host vehicle included in global positioning system (GPS) information based on determining that the error is smaller than a reference error,to compare a first width of a road on which the host vehicle is traveling and which is included in the map information and a second width based on a distance between the first stationary object and the second stationary object, to determine at least one of the first stationary object or the second stationary object as a road edge based on a difference between the first width and the second width being less than or equal to a first reference width, and to output a signal indicating the road edge.

[0006] The apparatus, wherein the processor is configured to determine that at least one of the first stationary object or the second stationary object is not a roadway edge based on the difference between the first width and the second width being greater than the first reference width.

[0007] The apparatus, wherein the processor is configured to generate a histogram based on a range and a second axis coordinate of the first reference point tracked on a plane formed by a first axis and the second axis, the range being divided by the grids, the first axis corresponding to a direction of travel of the host vehicle, and the second axis being perpendicular to the first axis.

[0008] The apparatus, wherein the processor is configured to generate the histogram based on the first reference point detected in the areas divided by the grids and sub-areas obtained by dividing the areas at a certain interval, and wherein the areas divided by the grids include areas for dividing lanes on which the host vehicle can respectively travel.

[0009] The device, wherein the processor is configured to determine at least one of a first coordinate of a second axis of the first reference point, a second coordinate of the second axis of the second reference point, or a third coordinate of the second axis of the third reference point, wherein the at least one of the first coordinate, the second coordinate, or the third reference point is detected on a plane formed by a first axis and the second axis perpendicular to the first axis, the first axis corresponding to a direction of travel of the host vehicle, and, based on the first coordinate of the second axis being greater than the second coordinate of the second axis, to determine that the first stationary object is located on a left side of the host vehicle, based on the first coordinate of the second axis being smaller than the second coordinate of the second axis,that the first stationary object is located on a right side of the host vehicle, to determine that the second stationary object is located on a left side of the host vehicle based on the first coordinate of the second axis being greater than the third coordinate of the second axis, or to determine that the second stationary object is located on a right side of the host vehicle based on the first coordinate of the second axis being less than the third coordinate of the second axis.

[0010] The apparatus, wherein the processor is configured to determine the first stationary object as a first roadway edge based on a length of the second virtual box being greater than or equal to a first reference length, virtual boxes each different from the second virtual box not existing in an area in which the second virtual box is detected, and a distance between the second reference point and the host vehicle being less than or equal to a first reference length.reference distance, and that the second virtual box includes a certain type of points with a second reference number or more, or to determine the second stationary object as a second road edge based on that a length of the third virtual box is greater than or equal to the first reference length, that virtual boxes each of which is different from the third virtual box do not exist in an area in which the third virtual box is detected, that a distance between the third reference point and the host vehicle is less than or equal to the first reference distance, and that the third virtual box includes a certain type of points with the second reference number or more.

[0011] The device, wherein the processor is configured to determine the first position and the second position in the grids to divide a plane formed by a first axis and a second axis, wherein the first axis corresponds to a direction of travel of the host vehicle and the second axis is perpendicular to the first axis, to determine a first error in a direction of the first axis based on a first coordinate of the first axis included in the first position and a second coordinate of the first axis included in the second position, to determine a second error in a direction of the second axis of the host vehicle based on a fourth coordinate of the second axis included in the first position and a fifth coordinate of the second axis included in the second position, and to determine the first width and the second width based on,that the first error is smaller than a first reference error and the second error is smaller than a second reference error.,

[0012] The apparatus, wherein the processor is configured to determine an area in which the host vehicle can travel from the areas divided by the grids, and to determine that at least one of the first stationary object or the second stationary object is not a roadway edge based on determining a stationary object different from at least one of the first stationary object or the second stationary object in an area adjacent to an area in which at least one of the first stationary object or the second stationary object exists.

[0013] The apparatus, wherein the processor is configured to determine at least one of the first stationary object or the second stationary object as a road edge based on at least one of a length of the second virtual box or a length of the third virtual box being greater than or equal to a second reference length, determine a first point closest to the host vehicle from points included in the second virtual box, determine a second point closest to the host vehicle from points included in the third virtual box, and determine at least one of the first stationary object or the second stationary object as a road edge based on a difference between a distance between the first point and the second point and a road width included in the map information being less than or equal to a second reference width.

[0014] According to the present disclosure, a method comprises determining a first reference point within a line segment corresponding to a rear side of an external vehicle, the line segment being one of line segments forming a first virtual box corresponding to the external vehicle detected by a sensor, removing, based on tracking the first reference point in areas divided by grids associated with frames of a particular section, points from a plurality of points obtained by the sensor relative to at least one of a second reference point located within a second line segment corresponding to a rear side of a first stationary object, the second line segment being one of the line segments forming a second virtual box corresponding to the first stationary object, or a third reference point,which is located within a third line segment corresponding to a back side of a second stationary object, wherein the third line segment is one of the line segments forming a third virtual box corresponding to the second stationary object, determining an error with respect to a position of a host vehicle by comparing a first position of the host vehicle included in map information received via a communication circuit and a second position of the host vehicle included in GPS information based on determining that the error is smaller than a reference error, comparing a first width of a road on which the host vehicle is traveling and which is included in the map information and a second width based on a distance between the first stationary object and the second stationary object,determining at least one of the first stationary object or the second stationary object as a road edge based on a difference between the first width and the second width being less than or equal to a first reference width, and outputting a signal indicative of the road edge.

[0015] The method further comprises determining that at least one of the first stationary object or the second stationary object is not a roadway edge based on the difference between the first width and the second width being greater than the first reference width.

[0016] The method further comprises generating a histogram based on a range and a second axis coordinate of the first reference point tracked on a plane formed by a first axis and the second axis, the range being divided by the grids, the first axis corresponding to a direction of travel of the host vehicle, and the second axis being perpendicular to the first axis.

[0017] The method further comprises generating the histogram based on the first reference point detected in the areas divided by the grids and sub-areas obtained by dividing the areas at a certain interval, and wherein the areas divided by the grids include areas for dividing lanes on which the host vehicle can travel, respectively.

[0018] The method further comprises determining at least one of a first coordinate of a second axis of the first reference point, a second coordinate of the second axis of the second reference point, or a third coordinate of the second axis of the third reference point, wherein the at least one of the first coordinate, the second coordinate, or the third reference point is detected on a plane formed by a first axis and the second axis perpendicular to the first axis, the first axis corresponding to a direction of travel of the host vehicle, and determining that the first stationary object is located on the left side of the host vehicle based on the first coordinate of the second axis being greater than the second coordinate of the second axis, determining that the first stationary object is located on a right side of the host vehicle based onthat the first coordinate of the second axis is less than the second coordinate of the second axis, determining that the second stationary object is located on a left side of the host vehicle based on the first coordinate of the second axis being greater than the third coordinate of the second axis, or determining that the second stationary object is located on a right side of the host vehicle based on the first coordinate of the second axis being less than the third coordinate of the second axis.

[0019] The method further comprises determining the first stationary object as a first road edge based on a length of the second virtual box being greater than or equal to a first reference length, virtual boxes each different from the second virtual box not being present in an area where the second virtual box is detected, a distance between the second reference point and the host vehicle being less than or equal to a first reference distance, and the second virtual box comprising a specific type of points with a second reference number or more, or determining the second stationary object as a second road edge based on a length of the third virtual box being greater than or equal to the first reference length, virtual boxes each different from the third virtual box not being present in an area where the third virtual box is detected,that a distance between the third reference point and the host vehicle is less than or equal to the first reference distance and that the third virtual box includes a certain type of points with the second reference number or more.,

[0020] The method further comprises determining the first position and the second position in the grids to divide a plane formed by a first axis and a second axis, wherein the first axis corresponds to a direction of travel of the host vehicle and the second axis is perpendicular to the first axis, determining a first error in a direction of the first axis based on a first coordinate of the first axis included in the first position and a second coordinate of the first axis included in the second position, determining a second error in a direction of the second axis of the host vehicle based on a fourth coordinate of the second axis included in the first position and a fifth coordinate of the second axis included in the second position, and comparing the first width and the second width based onthat the first error is smaller than a first reference error and the second error is smaller than a second reference error.,

[0021] The method further comprises determining an area in which the host vehicle can travel from the areas divided by the grids and determining that at least one of the first stationary object or the second stationary object is not a roadway edge based on determining a stationary object that is different from at least one of the first stationary object or the second stationary object in an area adjacent to an area in which at least one of the first stationary object is present.

[0022] The method further comprises determining at least one of the first stationary object or the second stationary object as a road edge based on at least one of a length of the second virtual box or a length of the third virtual box being greater than or equal to a second reference length, determining a first point closest to the host vehicle from points included in the second virtual box, determining a second point closest to the host vehicle from points included in the third virtual box, and determining at least one of the first stationary object or the second stationary object as a road edge based on a difference between a distance between the first point and the second point and a road width included in the map information being less than or equal to a second reference width. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other objects, features and advantages of the present disclosure will become more apparent from the following detailed description taken in conjunction with the accompanying drawings: Fig. 1 shows an example of a block diagram of a vehicle control device according to an example of the present disclosure; Fig. 2 shows an example of detecting an external object and a road edge by a vehicle control device according to an example of the present disclosure; Fig. 3 shows an example in which a vehicle control device generates a histogram by tracking an external vehicle according to an example of the present disclosure; Fig. 4 shows an example of outputting a road edge by a vehicle control device according to an example of the present disclosure; Fig. 5 shows an example in which a vehicle control device detects a road edge according to an example of the present disclosure; Fig. 6 shows an example of a flowchart of a vehicle control method according to an example of the present disclosure; Fig. 7 shows an example of a flowchart of a vehicle control method according to an example of the present disclosure; and Fig. 8 shows an example of a computer system associated with a vehicle control device according to an example of the present disclosure. DETAILED DESCRIPTION

[0024] Hereinafter, some examples of the present disclosure will be described in detail with reference to the accompanying drawings. When attaching reference numerals to components of each drawing, it should be noted that the same components will have the same reference numerals even if they are indicated in a different drawing. Furthermore, in describing the examples of the present disclosure, detailed descriptions of well-known functions or arrangements or configurations are omitted when they might unnecessarily obscure the subject matter of the present disclosure.

[0025] In describing elements of an example of the present disclosure, the terms first, second, A, B, (a), (b), and the like may be used herein. These terms are used only to distinguish one element from another, but do not limit the corresponding elements, regardless of the type, order, or priority of the corresponding elements. Furthermore, unless otherwise defined, all terms used herein, including technical and scientific terms, are to be interpreted as is customary in the art to which the present disclosure belongs.It is to be understood that the terms used herein are to be interpreted to have a meaning consistent with their meaning in the context of the present disclosure and the relevant prior art, and are not to be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0026] Below, various examples of the present disclosure are described with reference to the Fig. 1 to 8 described in detail.

[0027] Fig. 1 shows an example of a block diagram of a vehicle control device according to an example of the present disclosure.

[0028] With reference to Fig. 1, a vehicle control device 100 according to an example of the present disclosure may be implemented inside or outside a vehicle (e.g., host vehicle), and some of the components included in the vehicle control device 100 may be implemented inside or outside the vehicle. At this time, the vehicle control device 100 may be integrated into the internal control units of a vehicle and may be implemented with a separate device for connecting to the control units of the vehicle by means of a separate connection means. For example, the vehicle control device 100 may also include components included in Fig. 1 are not shown.

[0029] With reference to Fig. 1, according to one example, the vehicle control device 100 may include a processor 110, a sensor (e.g., a LiDAR 120), and a communication circuit 130. The processor 110, the LiDAR 120, or the communication circuit 130 may be electrically or operatively coupled to each other by an electronic component including a communication bus.

[0030] Hereinafter, the fact that hardware components are operatively coupled may include the fact that a direct and / or indirect connection is established between the hardware components, wired and / or wireless, such that the second hardware is controlled by the first hardware among the hardware components. Although various blocks are shown, an example is not limited thereto.

[0031] Some of the Fig. 1 may be included in a single integrated circuit, including a system-on-chip (SoC). The type and / or number of hardware included in the vehicle control device 100 is not limited to the hardware shown in Fig. 1. For example, the vehicle control device 100 may only implement some of the Fig. 1 hardware components shown.

[0032] The vehicle control device 100 according to one example may include hardware for processing data based on one or more instructions. The hardware for processing data may include the processor 110. The hardware for processing data may include, for example, an arithmetic and logic unit (ALU), a floating-point unit (FPU), a field-programmable gate array (FPGA), a central processing unit (CPU), and / or an application processor (AP). The processor 110 may have a single-core processor structure or may have a multi-core processor structure including a dual-core, a quad-core, a hexa-core, or an octa-core.

[0033] The vehicle control device 100 according to one example may include the LiDAR 120. For example, the LiDAR 120 may obtain data sets from identifying objects in the surroundings of the vehicle control device 100. For example, based on a pulsed laser signal emitted by the LiDAR 120 that is reflected and returned by the surrounding object, the LiDAR 120 may detect at least one of a location of the surrounding object, a direction of movement of the surrounding object, a speed of the surrounding object, or any combination thereof.

[0034] For example, the LiDAR 120 may obtain data sets comprising a plurality of points in the space defined by a first axis (e.g., an x-axis), a second axis (e.g., a y-axis), and a third axis (e.g., a z-axis) based on a pulsed laser signal reflected from surrounding objects. For example, the LiDAR 120 may obtain data sets comprising a plurality of points in the space defined by the first axis, the second axis, and the third axis based on receiving the pulsed laser signal in a certain period.

[0035] Hereinafter, the first axis may include the x-axis, the second axis may include the y-axis, and the third axis may include the z-axis. However, the first axis, the second axis, and the third axis, respectively referred to as the "x-axis," "y-axis," and "z-axis," are not limited to the above descriptions.

[0036] The processor 110, which is included in the vehicle control device 100 according to one example, may emit light from a host vehicle using the LiDAR 120. For example, the processor 110 may receive light emitted by the host vehicle. For example, based on a time taken to transmit light emitted by the host vehicle and a time taken to receive light emitted by the host vehicle, the processor 110 may detect at least one of a location, a speed, or a direction of movement, or any combination thereof, of a surrounding object.

[0037] For example, the processor 110 may obtain data sets including a plurality of points based on the time required to transmit light emitted from the host vehicle and the time required to receive light emitted from the host vehicle. The processor 110 may obtain data sets expressing a plurality of points in a three-dimensional virtual coordinate system including the first axis, the second axis, and the third axis.

[0038] The communication circuit 130, which is included in the vehicle control device 100 according to one example, may include a hardware component for supporting transmission and / or reception of signals between the vehicle control device 100 and an external electronic device (or an external vehicle). For example, the communication circuit 130 may include at least one of a modem, an antenna, or an optical / electronic converter (O / E), or any combination thereof.

[0039] For example, the communication circuit 130 may support transmission and / or reception of signals based on various protocols, including at least one of Ethernet, Local Area Network (LAN), Wide Area Network (WAN), Wireless Fidelity (WiFi), Bluetooth, Bluetooth Low Energy (BLE), ZigBee, Long Term Evolution (LTE), 5G New Radio (NR), Controller Area Network (CAN), or Local Interconnect Network (LIN), or any combination thereof.

[0040] The processor 110, which is included in the vehicle control device 100 according to an example, may obtain a first virtual box corresponding to an external vehicle detected by the LiDAR 120. The processor 110 may detect a first reference point within a line segment corresponding to a rear side of the external vehicle among line segments constituting the first virtual box based on obtaining a first virtual box corresponding to the external vehicle detected by the LiDAR 120.

[0041] The number of first virtual boxes is not limited to one. For example, the processor 110 included in the vehicle control device 100 can recognize virtual boxes corresponding to external vehicles. The processor 110 can recognize reference points included in the virtual boxes corresponding to the external vehicles, respectively. For convenience, descriptions will be given below with respect to the first virtual box corresponding to an external vehicle.

[0042] In one example, processor 110 may track a first reference point during frames of a particular portion in grid-divided regions. For example, processor 110 may track the first reference point in the grid-divided regions for the particular number of frames (e.g., about 10 frames).

[0043] For example, the processor 110 may recognize partial regions obtained by dividing the regions divided by grids at a certain interval.

[0044] The areas divided by grids can be referred to, for example, as "lane grids." The sub-areas can be referred to, for example, as "road bim (RB) grids."

[0045] In one example, the processor 110 may detect the first reference point in areas indicating a road and the sub-areas obtained by dividing the areas indicating the road at a certain interval. The processor 110 may track the first reference point in the areas indicating a road and the sub-areas obtained by dividing the areas representing the road at a certain interval.

[0046] The processor 110 may generate a histogram based on the first reference point in areas indicating a road and sub-areas obtained by dividing the areas indicating the road at a certain interval.

[0047] In one example, processor 110 may track the first reference point on a plane formed by the first axis and the second axis below the first axis, the second axis, and the third axis. Processor 110 may detect the coordinates of the first reference point tracked on a plane formed by the first axis and the second axis below the first axis, the second axis, and the third axis.

[0048] Processor 110 may generate a histogram based on tracking the first reference point during frames of a particular portion within the grid-divided regions. The first reference point may be referred to, for example, as a "tracking point for tracking an external vehicle."

[0049] In one example, processor 110 may detect a second reference point located within a line segment corresponding to a back surface of a first stationary object from line segments forming a second virtual box corresponding to the first stationary object. Processor 110 may detect a third reference point located within a line segment corresponding to a back surface of a second stationary object from line segments forming a third virtual box corresponding to the second stationary object. For example, the second reference point may be referred to as a "tracking point for tracking the first stationary object." The third reference point may be referred to as a "tracking point for tracking the second stationary object," for example.

[0050] For example, the rear side of the first stationary object and / or the rear side of the second stationary object may include a direction opposite to a direction in which the host vehicle travels. For example, if the direction in which the host vehicle travels is a positive direction of the first axis among the first axis, the second axis, and the third axis, the rear side of the first stationary object and / or the rear side of the second stationary object may include a surface (or a line segment) corresponding to a point detected by the smallest coordinate among coordinates of a direction of the first axis.

[0051] In one example, based on the second reference point located within a line segment corresponding to the rear of the first stationary object among line segments forming the second virtual box corresponding to the first stationary object and / or the third reference point located within a line segment corresponding to the rear of the second stationary object among line segments forming the third virtual box corresponding to the second stationary object, the processor 110 may identify at least one of an area in which the host vehicle can travel, an area different from the area in which the host vehicle can travel, or any combination thereof.

[0052] For example, the processor 110 may identify an area between the second reference point and the third reference point as an area in which the host vehicle can travel. For example, the processor 110 may identify an area different from the area between the second reference point and the third reference point as an area different from the area in which the host vehicle can travel. For example, the area different from the area in which the host vehicle can travel may include an area outside a roadway edge.

[0053] In one example, based on tracking the first reference point in grid-divided areas during frames of a particular section, the processor 110 may remove points that are in an area different from the area in which the host vehicle can travel, among points obtained by the LiDAR 120, relative to at least one of the second reference point located within the line segment corresponding to the back of the first stationary object, among line segments forming the second virtual box corresponding to the first stationary object, or the third reference point located within the line segment corresponding to the back of the second stationary object, among line segments forming the third virtual box corresponding to the second stationary object, or any combination thereof.

[0054] For example, the processor 110 may initialize a histogram using points that are in a different range than the range in which the host vehicle can travel.

[0055] In one example, processor 110 may receive map information including a first position of the host vehicle via communication circuit 130. For example, the map information may include accurate map information. For example, processor 110 may receive the accurate map information including the first position of the host vehicle via communication circuit 130.

[0056] The precise map information may, for example, include at least one of first information for determining whether the host vehicle has entered a precise map section, second information relating to an accuracy of the longitudinal positioning of the host vehicle, third information relating to an accuracy of the lateral positioning of the host vehicle, or fourth information relating to a position of the host vehicle and the number of lanes in which the host vehicle is traveling, or any combination thereof.

[0057] For example, the longitudinal positioning accuracy of the host vehicle may include the position accuracy in a direction of the first axis on a plane formed by the first axis and the second axis. For example, the longitudinal positioning accuracy of the host vehicle may include the position accuracy in a direction of the second axis on a plane formed by the first axis and the second axis. For example, the fourth information regarding the position of the host vehicle and the number of lanes the host vehicle travels on may include information regarding the position of the host vehicle and a lane the host vehicle travels on based on the rear wheel axle of the host vehicle.

[0058] For example, based on the accurate map information, processor 110 may detect at least one of the host vehicle's longitudinal positioning accuracy, the host vehicle's lateral positioning accuracy, or any combination thereof. For example, at least one of the host vehicle's longitudinal positioning accuracy, the host vehicle's lateral positioning accuracy, or any combination thereof may relate to an error between the host vehicle's position included in the GPS information and a host vehicle's position included in the accurate map information.

[0059] In one example, processor 110 may obtain the GPS information. For example, processor 110 may receive the GPS information from an external electronic device (e.g., a server) via communication circuit 130, or may obtain the GPS information from a vehicle control system (or a computer system) related to vehicle control device 100.

[0060] In one example, processor 110 may compare the first position of the host vehicle with a second position of the host vehicle included in the GPS information based on receiving the accurate map information including the first position of the host vehicle via communication circuit 130. Processor 110 may detect an error with respect to a position of the host vehicle based on the second position.

[0061] For example, in a two-dimensional virtual coordinate system consisting of a first and a second axis, the processor 110 may detect an error in the position of the host vehicle based on the second position included in the GPS information.

[0062] In one example, the processor 110 may determine, based on the second position, whether the error in the position of the host vehicle is smaller in magnitude / value than a reference error. Based on the fact that the error in the position of the host vehicle is determined to be smaller than the reference error based on the second position, the processor 110 may compare a first width of a road on which the host vehicle is traveling and which is included in the accurate map with a second width based on a distance between a first stationary object and a second stationary object. For example, the distance between the first stationary object and the second stationary object may include a distance between the second virtual box and the third virtual box.

[0063] In one example, processor 110 may detect a difference between the first width and the second width. Processor 110 may detect at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on the difference between the first width and the second width being less than or equal to a first reference width. Processor 110 may output the detected roadway edge based on at least one of the first stationary object or the second stationary object, or any combination thereof, being the roadway edge.

[0064] For example, the processor 110 may assign an identifier (e.g., RoadEdge) indicating a road edge to a stationary object detected as a road edge from the first stationary object and the second stationary object based on at least one of the first stationary object or the second stationary object, or a combination thereof, being the road edge.

[0065] In one example, the processor 110 may not recognize at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on the difference between the first width and the second width being greater than the first reference width.

[0066] In one example, the processor 110 may detect at least one of a position of the first reference point, a position of the second reference point, or a position of the third reference point, or any combination thereof, detected on a plane formed by the first axis and the second axis below the first axis, the second axis, and the third axis.

[0067] The processor 110 may detect a direction in which at least one of the first stationary object or the second stationary object, or any combination thereof, is located relative to the host vehicle based on at least one of the position of the first reference point, the position of the second reference point, or the position of the third reference point, or any combination thereof detected on the plane formed by the first axis and the second axis below the first axis, the second axis, and the third axis.

[0068] For example, the processor 110 may detect at least one of a first coordinate of a second axis of the first reference point, a second coordinate of a second axis of the second reference point, or a third coordinate of a second axis of the third reference point, or any combination thereof.

[0069] The processor 110 may compare at least one of the first coordinate of the second axis, the second coordinate of the second axis, or the third coordinate of the second axis, or a combination thereof.

[0070] For example, processor 110 may compare the first coordinate of the second axis to the second coordinate of the second axis. Based on the first coordinate of the second axis being greater than the second coordinate of the second axis, processor 110 may determine that the first stationary object is farther to the left than the host vehicle.

[0071] For example, based on the first coordinate of the second axis being smaller than the second coordinate of the second axis, the processor 110 may detect that the first stationary object is farther to the right than the host vehicle.

[0072] For example, processor 110 may compare the first coordinate of the second axis with the second coordinate of the second axis. Based on the first coordinate of the second axis being greater than the third coordinate of the second axis, processor 110 may determine that the second stationary object is farther to the left than the host vehicle.

[0073] For example, based on the first coordinate of the second axis being smaller than the third coordinate of the second axis, the processor 110 may detect that the second stationary object is farther to the right than the host vehicle.

[0074] In one example, the processor 110 may recognize the first position included in the accurate map information and the second position included in the GPS information in grids to divide a plane formed by the first axis and the second axis among the first axis, the second axis, and the third axis.

[0075] The processor 110 may detect a first coordinate of the first axis included in the first position. The processor 110 may detect a second coordinate of the first axis included in the second position. The processor 110 may detect a first error of a direction of the first axis of the host vehicle based on the first coordinate of the first axis and the second coordinate of the first axis.

[0076] The processor 110 may detect a fourth coordinate of the second axis included in the first position. The processor 110 may detect a fifth coordinate of the second axis included in the second position. The processor 110 may detect a second error of a direction of the second axis of the host vehicle based on the fourth coordinate of the second axis and the fifth coordinate of the second axis.

[0077] In one example, processor 110 may determine whether the first error is less than a first reference error (e.g., about 5 m). Processor 110 may determine whether the second error is less than a second reference error (e.g., about 2 m).

[0078] The processor 110 may compare a first width to a second width based on the first error being less than the first reference error and the second error being less than the second reference error. The processor 110 may identify at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on a difference between the first width and the second width being less than or equal to a first reference width.

[0079] In one example, the processor 110 may identify an area in which the host vehicle can travel among areas divided by grids. In one example, the processor 110 may identify an area adjacent to the area in which the host vehicle can travel among areas divided by grids.

[0080] The processor 110 may detect at least one of the first stationary object or the second stationary object, or any combination thereof, in an area adjacent to the area in which the host vehicle can travel. The processor 110 may detect at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on detecting at least one of the first stationary object or the second stationary object, or any combination thereof, in an area adjacent to the area in which the host vehicle can travel.

[0081] In one example, based on detecting a stationary object that is different from at least one of the first stationary object or the second stationary object, or any combination thereof, in an area adjacent to an area in which at least one of the first stationary object or the second stationary object, or any combination thereof, is present, the processor 110 may not detect at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge.

[0082] In one example, processor 110 may detect a length of the second virtual box corresponding to the first stationary object. Processor 110 may detect a length of the third virtual box corresponding to the second stationary object.

[0083] In one example, the processor 110 may identify at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on at least one of the length of the second virtual box or the length of the third virtual box, or any combination thereof, being greater than or equal to a second reference length.

[0084] In one example, processor 110 may detect a first point closest to the host vehicle among points encompassed in the second virtual box. Processor 110 may detect a second point closest to the host vehicle among points encompassed in the third virtual box.

[0085] In one example, processor 110 may detect a distance between the first point and the second point. Processor 110 may detect a difference between the road widths included in the accurate map information. Processor 110 may determine whether the difference between a road width included in the accurate map information and the distance between the first point and the second point is less than or equal to the second reference width (e.g., approximately 3.5 m).

[0086] The processor 110 may recognize at least one of the first stationary object or the second stationary object, or any combination thereof, as a road edge based on the fact that the difference between the distance between the first point and the second point and the road width included in the accurate map information is less than or equal to the second reference width. For example, at least one of the above-mentioned first point or the above-mentioned second point, or any combination thereof, may include a vertex included in at least one of the second virtual box or the third virtual box, or any combination thereof.

[0087] As described above, according to one example, the processor 110 of the vehicle control device 100 can recognize at least one of the first stationary object or the second stationary object, or any combination thereof, as a road edge based on the first reference point. Even if occlusion occurs or a boundary object is lost, the processor 110 can accurately detect a road edge by recognizing at least one of the first stationary object or the second stationary object, or any combination thereof, as a road edge based on the first reference point.

[0088] Fig. 2 shows an example of detection of an external object and a roadway edge (e.g., a grass verge, a concrete or stone curb, a breakdown shoulder or bike path, a drainage ditch, reflective markings or boundary lines, guardrails, trees, shrubs, or painted lines, etc.) by a vehicle control device according to an example of the present disclosure.

[0089] With reference to Fig. 2, a processor included in the vehicle control device according to an example may detect an environment of a host vehicle, including a first example 201. For example, the processor may detect the environment of a host vehicle based on at least one of a camera or a sensor (e.g., LiDAR), or any combination thereof. While detecting the environment of the host vehicle, the processor may detect an external object 210 located outside a roadway edge. The external object 210 must be detected as a stationary object located outside the roadway edge.

[0090] A second example 203 may include an example of generating boxes based on points generated by a LiDAR included in a vehicle control device.

[0091] For example, in the second example 203, a virtual box 220 may correspond to the external object 210 in a first example 201. The processor must recognize the virtual box 220 as a stationary object located outside the roadway edge. However, if the stationary object is near the roadway edge (e.g., within a threshold distance), the virtual box 220 may be recognized as an object inside the roadway edge. Furthermore, the virtual box 220 may be recognized as a moving object entering the inside of the roadway edge from the outside of the roadway edge, rather than as the stationary object located outside the roadway edge. The outside of the roadway edge may, for example, be referred to as an "area in which the host vehicle cannot travel" (e.g.,a drainage ditch, an unpaved road such as gravel or dirt roads, raised pavement markings, trees, shrubs, guardrails, etc.). For example, the inside or interior of the roadway shoulder may be referred to as an "area within which the host vehicle can travel."

[0092] If it is detected that the virtual box 220 enters the inside of the road edge from the outside of the road edge, a failure of a vehicle control system associated with the vehicle control device may occur. For example, since the virtual box 220 enters the inside of the road edge from the outside of the road edge, the vehicle control system associated with the vehicle control device may perform an operation of adjusting the speed of the host vehicle or changing a travel route of the host vehicle. Since the travel of the host vehicle is unstable, the vehicle drive system associated with the vehicle control device performs an operation of adjusting the speed of the host vehicle or changing the travel route of the host vehicle. Accordingly, there is a need for a solution to the unstable travel of the host vehicle.

[0093] Fig. 3 shows an example in which a vehicle control device generates a histogram by tracking an external vehicle according to an example of the present disclosure.

[0094] With reference to Fig. 3, according to one example, a processor included in a vehicle control device may detect a first virtual box 310 corresponding to an external vehicle. The processor may detect a first reference point 311 of a first virtual box 310 corresponding to an external vehicle. For example, the processor may detect the first reference point 311 within a line segment corresponding to a rear side of the external vehicle among line segments constituting the first virtual box 310.

[0095] The processor may track the first reference point 311. For example, the processor may track the first reference point 311 during frames of the particular section. For example, the frames of the particular section may include approximately 10 frames.

[0096] In one example, the processor may generate a histogram 315 based on points 313 tracked during frames of the particular portion.

[0097] For example, the processor may generate the histogram 315 based on grids 301 for dividing a lane and subgrids 303 obtained by dividing the grids 301 at a certain interval.

[0098] In one example, based on generating the histogram 315, the processor may identify a virtual box 320 corresponding to a roadway edge (e.g., a grass verge, a concrete or stone curb, a hard shoulder or bike lane, a drainage ditch, reflective markings or delineations, guardrails, trees, shrubs, or painted lines, etc.). For example, the virtual box 320 corresponding to a roadway edge may be assigned a particular identifier. The identifier may, for example, include an identifier indicating that the virtual box 320 is a roadway edge.

[0099] In one example, the processor may remove points that lie outside a region in which the virtual box 320 corresponding to the roadway edge is detected or detected. For example, the outside of a region in which the virtual box 320 is detected or detected may include a region in which the first reference point 311 of the virtual box 310 corresponding to the external vehicle is not detected or detected.

[0100] In one example, the processor may detect the virtual box 320 as a stationary object (e.g., a concrete or stone curb, guardrails, trees, shrubs, a street sign post, etc.) based on the generated histogram 315 and then determine that the detected stationary object is a roadway edge. The process of determining the virtual box 320 as a roadway edge will be described later.

[0101] Fig. 4 shows an example of outputting a road edge by a vehicle control device according to an example of the present disclosure.

[0102] With reference to Fig. 4, a processor included in a vehicle control device may detect roadway edges 413 and 415 according to one example.

[0103] For example, if the processor fails to determine a lane edge based on the Fig. 3, it can generate candidates for road edges based on virtual boxes corresponding to external objects.

[0104] In one example, while a host vehicle 411 is traveling, the processor may detect the virtual boxes corresponding to the external objects. While the host vehicle 411 is traveling, the processor may detect a road edge based on the external objects.

[0105] For example, the processor may detect a plurality of virtual boxes in the first area 413.

[0106] In one example, the processor may determine a length occupied by the plurality of virtual boxes based on detecting the plurality of virtual boxes. For example, the length occupied by the plurality of virtual boxes may be detected based on a direction of a first axis among the first axis, a second axis, and a third axis. For example, the first axis may be referred to as the x-axis, the second axis may be referred to as the y-axis, and the third axis may be referred to as the z-axis. However, an example is not limited thereto.

[0107] For example, the length occupied by the plurality of virtual boxes may include a length from a minimum coordinate of the first axis to a maximum coordinate of the first axis.

[0108] For example, the processor may detect a road edge corresponding to the plurality of virtual boxes based on the length occupied by the plurality of virtual boxes being greater than or equal to a reference length (e.g., approximately 10-20 m) and the number of points having a particular type among points included in the plurality of virtual boxes being greater than or equal to a reference number (e.g., approximately 10-20). For example, the particular type of points may be referred to as "clearance points." The clearance points may be detected, for example, based on receiving light emitted by a LiDAR at a particular interval.

[0109] In one example, the processor may detect a virtual box in the second region 415. For example, the processor may detect a single virtual box as a roadway edge using a histogram based on detecting the single virtual box. For example, the histogram may be generated based on points tracking a moving object, including a vehicle.

[0110] As described above, according to one example, the processor of the vehicle control device may detect a virtual box using a histogram as the lane edge. The processor may detect the virtual box using the histogram as the lane edge, thereby reducing an error in the vehicle control system associated with the vehicle control device.

[0111] Fig. 5 shows an example in which a vehicle control device detects a road edge according to an example of the present disclosure.

[0112] With reference to Fig. 5, according to one example, a processor included in a vehicle control device may detect areas divided by a plurality of grids. For example, based on areas divided by a plurality of grids, the processor may detect a grid 511 corresponding to a lane in which the host vehicle is traveling.

[0113] For example, based on reference points for tracking an external vehicle, the processor may identify an area 513 (e.g., a paved road) in which the host vehicle can travel. The processor may identify virtual boxes 515 and 519 in an area other than the area 513 in which the host vehicle can travel. For example, the virtual boxes 515 and 519 may include virtual boxes 515 and 519, each output as roadway edges.

[0114] For example, the processor may perform a check to determine whether virtual boxes 515 and 519 each correspond to lane edges. For example, from areas divided by a plurality of grids, the processor may determine that areas where virtual boxes 515 and 519 are detected are lane edges 523 and 525.

[0115] The processor may check the roadway edges 523 and 525. For example, the processor may determine whether a stationary object (e.g., a mailbox, a street sign post, etc.) is located in areas adjacent to the areas detected as roadway edges 523 and 525.

[0116] For example, the processor may determine from the plurality of grids whether a stationary object is located in an area adjacent to grids (e.g., grid 5 and grid 11) identified as roadway edges 523 and 525. For example, the processor may determine whether the stationary object is located in the area 513 in which the host vehicle can travel between roadway edges 523 and 525.

[0117] For example, the processor can Fig. 5 determine whether a stationary object is located in grid 6 adjacent to grid 5 determined as the road edge. For example, the processor may determine whether the stationary object is present in grid 10 adjacent to grid 11 determined as the road edge. For example, each of grids 6 and 11 described above may be referred to as a grid adjacent to a grid determined as the road edge within a range in which the host vehicle can travel.

[0118] In one example, the processor may determine a size of each of the virtual boxes 515 and 519. For example, the processor may detect at least one of a width or a length, or any combination, of each of the virtual boxes 515 and 519. The processor may determine whether to output the virtual boxes 515 and 519 as lane edges based on detecting at least one of the width or the length, or any combination, of each of the virtual boxes 515 and 519.

[0119] For example, based on the length of each of the virtual boxes 515 and 519 exceeding a reference length (e.g., approximately 10-20 m), the processor may detect that the virtual boxes 515 and 519 are roadway edges, and may then output the detected roadway edges. For example, the length of each of the virtual boxes 515 and 519 may include the length of the direction of the first axis.

[0120] In one example, the processor may include reference points included in virtual boxes 515 and 519, respectively. For example, the processor may detect the vertices 517 and 521 closest to the host vehicle from vertices forming virtual boxes 515 and 519. The processor may detect each of virtual boxes 515 and 519 as a road edge based on the fact that the length of each of vertices 517 and 521 tracked during frames of the designated section is less than a reference length (e.g., about 10-20 m), and then output the detected road edge.

[0121] Fig. 6 shows an example of a flowchart of a vehicle control method according to an example of the present disclosure.

[0122] In the following, it is assumed that the vehicle control device 100 of Fig. 1 the process of Fig. 6. Additionally or alternatively, a description of Fig. 6 that an operation described as being performed by a device is controlled by the processor 110 of the vehicle control device 100.

[0123] At least one of the processes from Fig. 6 can be from the vehicle control device 100 Fig. 1. Each of the operations in Fig. 6 can be performed sequentially, but need not be performed sequentially. For example, the order of operations can be changed, and at least two operations can be performed in parallel.

[0124] With reference to Fig. 6, a vehicle control method according to an example may include, in operation S601, a process of generating a histogram based on detecting a moving object. For example, the vehicle control method may include a process of generating the histogram based on detecting the moving object corresponding to an external vehicle.

[0125] For example, the vehicle control method may include a process of detecting a reference point of a virtual box corresponding to the moving object. The vehicle control method may include a process of tracking a reference point during frames of a specific section based on detecting the reference point of the virtual box corresponding to the moving object. The vehicle control method may include a process of generating the histogram based on tracking the reference point during the frames of the specific section.

[0126] In operation S603, according to one example, the vehicle control method may include an operation of detecting a stationary object. The vehicle control method may include an operation of initializing a part of the histogram based on detecting the stationary object. For example, the vehicle control method may include an operation of initializing a histogram in a range different from a range in which the reference point is detected. For example, the vehicle control method may include an operation of initializing the histogram of a range in which the stationary object is detected and a range different from a range in which a reference point included in the moving object is detected.

[0127] The operation of initializing the histogram may, for example, include an operation of removing a value from the histogram.

[0128] In operation S605, the vehicle control method according to an example may include a process of determining whether to generate a histogram based on the determined number of frames. For example, the determined number of frames may include approximately 10 frames.

[0129] When the histogram is not generated based on the determined number of frames (No in operation S605), the vehicle control method according to an example may include an operation of generating a histogram by additionally or alternatively detecting or sensing a moving object.

[0130] When the histogram is generated based on the determined number of frames (Yes in operation S605), the vehicle control method according to an example may include an operation of generating candidates for the lane edge.

[0131] The vehicle control method may, for example, include an operation of selecting the detected stationary object as a candidate included in the candidates for the road edge.

[0132] In operation S609, according to an example, the vehicle control method may include an operation of receiving accurate map information. For example, the vehicle control method may include an operation of receiving the accurate map information via a communication circuit. For example, the accurate map information may include at least one of first information regarding whether a host vehicle has entered a section using the accurate map information, second information regarding an accuracy of the longitudinal positioning of the host vehicle, third information regarding an accuracy of the lateral positioning of the host vehicle, or fourth information regarding a lane in which the host vehicle is traveling, or any combination thereof.

[0133] In operation S611, the vehicle control method according to an example may include an operation of recognizing whether the accurate map information is valid.

[0134] When the accurate map information is invalid (No in operation S611), the vehicle control method according to an example may include an operation of receiving the accurate map information again.

[0135] According to one example, if the accurate map information is valid (Yes in operation S611), the vehicle control method may include an operation of detecting a road width based on the accurate map information. For example, the vehicle control method may include an operation of detecting the road width based on the road information included in the accurate map information. For example, the vehicle control method may include an operation of detecting the road width corresponding to a width between lane edges.

[0136] In operation S615, the vehicle control method according to an example may include an operation of determining whether a difference between a first road width based on the candidates for the road edge and a second road width included in the accurate map information is less than or equal to a reference width (e.g., about 3.5 m).

[0137] The vehicle control method according to an example may include an operation of recognizing the first road width based on a distance between a first candidate located on the left side of the host vehicle and a second candidate located on the right side of the host vehicle among the candidates included in the road edge candidates.

[0138] The vehicle control method according to an example may include a process of detecting whether a difference between the first road width based on the lane edge candidates and the second road width included in the accurate map information is less than or equal to the reference width.

[0139] The reference width may, for example, include a width corresponding to a lane.

[0140] According to an example, when the difference between the first road width based on the lane edge candidates and the second road width included in the accurate map information is less than or equal to the reference width (Yes in operation S615), the vehicle control method may include a process of outputting the lane edge candidates in operation S617. For example, the vehicle control method may include a process of outputting a candidate included in the lane edge candidates.

[0141] Fig. 7 shows an example of a flowchart of a vehicle control method according to an example of the present disclosure.

[0142] In the following, it is assumed that the vehicle control device 100 of Fig. 1 the process of Fig. 7. Additionally or alternatively, a description of Fig. 7 that an operation described as being performed by a device is controlled by the processor 110 of the vehicle control device 100.

[0143] At least one of the processes in Fig. 7 can be controlled by the vehicle control device 100 of Fig. 1. Each of the operations in Fig. 7 can be performed sequentially, but need not be performed sequentially. For example, the order of operations can be changed, and at least two operations can be performed in parallel.

[0144] With reference to Fig. 7, a vehicle control method in operation S701 may include an operation of detecting a first reference point within a line segment corresponding to a rear side of an external vehicle among line segments constituting a first virtual box based on obtaining the first virtual box corresponding to the external vehicle detected by a LiDAR.

[0145] According to one example, the vehicle control method may include a process of generating a histogram based on an area divided by the grids based on a second-axis coordinate of the first reference point traced on a plane formed by a first axis and the second axis among the first axis, the second axis, and a third axis. For example, the first axis may include an x-axis. The second axis may include, for example, a y-axis. The third axis may include, for example, a z-axis. However, the first axis, the second axis, and the third axis are not limited to the above examples.

[0146] According to one example, the vehicle control method may include a process of generating the histogram based on the first reference point detected in the areas divided by the grids and sub-areas obtained by dividing the areas at a certain interval. The areas divided by the grids may include areas for dividing lanes on which the host vehicle can travel, respectively.

[0147] In operation S703, the vehicle control method according to an example may include an operation of removing points located in an area different from an area in which a host vehicle can travel, from points obtained by a LiDAR, relative to at least one of a second reference point of a second virtual box corresponding to a back side of a first stationary object among line segments constituting the first stationary object, or a third reference point of a third virtual box corresponding to a back side of a second stationary object among line segments constituting the second stationary object, or any combination thereof, based on tracking a first reference point in areas divided by grids during frames of a certain section.

[0148] In operation S705, the vehicle control method according to an example may include an operation of detecting an error with respect to a position of the host vehicle based on a second position by comparing a first position of the host vehicle and the second position of the host vehicle included in GPS information based on receiving accurate map information including the first position of the host vehicle via a communication circuit.

[0149] In operation S707, the vehicle control method according to an example may include an operation of comparing a first width of a road on which the host vehicle travels and which is included in the accurate map information with a second width based on a distance between the first stationary object and the second stationary object based on detecting that the error is smaller than a reference error.

[0150] The vehicle control method according to an example may include an operation of detecting at least one of a first coordinate of a second axis of the first reference point, a second coordinate of the second axis of the second reference point, or a third coordinate of the second axis of the third reference point, or any combination thereof, which is detected on a plane formed by the first axis and the second axis among the first axis, the second axis, and the third axis.The vehicle control method according to an example may include an operation of detecting that the first stationary object is farther to a left side than the host vehicle based on the first coordinate of the second axis being greater than the second coordinate of the second axis, detecting that the first stationary object is farther to a right side than the host vehicle based on the first coordinate of the second axis being smaller than the second coordinate of the second axis, detecting that the second stationary object is farther to a left side than the host vehicle based on the first coordinate of the second axis being greater than the third coordinate of the second axis, or detecting that the second stationary object is farther to a right side than the host vehicle based on the first coordinate of the second axis being smaller than the third coordinate of the second axis.

[0151] The vehicle control method according to an example may include a process of detecting the first position and the second position in the grids for dividing a plane formed by the first axis and the second axis among the first axis, the second axis, and the third axis, detecting a first error of a direction of the first axis of the host vehicle based on a first coordinate of the first axis included in the first position and a second coordinate of the first axis included in the second position, detecting a second error of a direction of the second axis of the host vehicle based on a fourth coordinate of the second axis included in the first position and a fifth coordinate of the second axis included in the second position, and comparing the first width with the second width based onthat the first error is smaller than a first reference error and the second error is smaller than a second reference error.,

[0152] In operation S709, according to an example, the vehicle control method may include an operation of recognizing at least one of the first stationary object or the second stationary object, or any combination thereof, as a road edge based on the difference between the first width and the second width being less than or equal to a first reference width.

[0153] According to one example, the vehicle control method may include an operation in which, based on the difference between the first and second widths being greater than the first reference width, at least one of the first stationary object or the second stationary object, or any combination thereof, is not recognized as a road edge.

[0154] According to one example, the vehicle control method may include an operation of recognizing an area in which the host vehicle can travel from areas divided by the grids, and not recognizing at least one of the first stationary object or the second stationary object or any combination thereof as a road edge, based on recognizing a stationary object different from at least one of the first stationary object or the second stationary object or any combination thereof in an area adjacent to an area in which at least one of the first stationary object or the second stationary object or any combination thereof exists.

[0155] According to one example, the vehicle control method may include a process of recognizing the first stationary object as a first road edge based on the fact that a length of the second virtual box is greater than or equal to a first reference length, that virtual boxes each different from the second virtual box do not exist in an area in which the second virtual box is recognized, that a distance between the second reference point and the host vehicle is less than or equal to a first reference distance, and the second virtual box includes the specific one of points with the second reference number or more, or recognizing the second stationary object as a second road edge based on the fact that a length of the third virtual box is greater than or equal to the first reference length, that virtual boxes each different from the third virtual box do not exist in an area,in which the third virtual box is detected that a distance between the third reference point and the host vehicle is less than or equal to the first reference distance and the third virtual box includes the specific type of points with the second reference number or more.,

[0156] According to one example, the vehicle control method may include an act of recognizing at least one of the first stationary object or the second stationary object, or any combination thereof, as a road edge based on at least one of a length of the second virtual box or a length of the third virtual box, or any combination thereof, being greater than or equal to a second reference length.

[0157] According to one example, the vehicle control method may include an operation of detecting a first point closest to the host vehicle among points included in the second virtual box, detecting a second point closest to the host vehicle among points included in the third virtual box, and detecting at least one of the first stationary object or the second stationary object or any combination thereof as a road edge based on the fact that a difference between a distance between the first point and the second point and a road width included in the accurate map information is less than or equal to a second reference width.

[0158] Fig. 8 shows an example of a computer system associated with a vehicle control device according to an example of the present disclosure.

[0159] With reference to Fig.8, a computer system 1000 may include at least a processor 1100, a memory 1300, a user interface input device 1400, a user interface output device 1500, a storage 1600, and a network interface 1700 interconnected via a bus 1200.

[0160] Processor 1100 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in memory 1300 and / or storage 1600. Both memory 1300 and storage 1600 may include various types of volatile or non-volatile storage media. For example, memory 1300 may include read-only memory (ROM) and random access memory (RAM).

[0161] Accordingly, the operations or algorithms described in connection with the examples disclosed in the patent specification may be implemented directly with a hardware module or a software module, or a combination of hardware and software modules, executed by the processor 1100. The software module may be located on a storage medium (i.e., the memory 1300 and / or the storage 1600), such as random access memory (RAM), flash memory, read-only memory (ROM), erasable and programmable ROM (EPROM), electrically EEPROM (EEPROM), a register, a hard disk drive, a removable disk, or a compact disc-ROM (CD-ROM).

[0162] The storage medium may be coupled to the processor 1100. The processor 1100 may read information from the storage medium and write information to the storage medium. Alternatively or additionally, the storage medium may be integrated with the processor 1100. The processor and the storage medium may be implemented with an application-specific integrated circuit (ASIC). The ASIC may be provided in a user terminal. Alternatively or additionally, the processor and the storage medium may be implemented with separate components in the user terminal.

[0163] The present disclosure has been made to solve the above-mentioned problems of the prior art while maintaining the advantages achieved by the prior art.

[0164] An example of the present disclosure provides a vehicle control device for detecting a road edge using a histogram generated based on tracking a moving object and a corresponding method.

[0165] An example of the present disclosure provides a vehicle control device for recognizing an area in which a host vehicle can travel using width information and distance information between virtual boxes included in map information, and a method therefor.

[0166] An example of the present disclosure provides a vehicle control device for reducing the occurrence of errors in a vehicle control system associated with a vehicle control device by accurately detecting a road edge and a method therefor.

[0167] The technical problems to be solved by the present disclosure are not limited to the aforementioned problems, and any other technical problems not mentioned here will be clearly understood by a person skilled in the art to which the present disclosure relates from the following description.

[0168] According to one example of the present disclosure, a vehicle control device may include a LiDAR (Light Detection and Ranging) and a processor. The processor may detect a first reference point within a line segment corresponding to a rear side of an external vehicle, among line segments forming a first virtual box, based on obtaining the first virtual box corresponding to the external vehicle detected by the LiDAR. It may remove points located in an area different from an area in which a host vehicle can travel from points obtained by the LiDAR, relative to at least one of a second reference point located within a line segment corresponding to a rear side of a first stationary object, among line segments forming a second virtual box corresponding to the first stationary object, or a third reference point.which is located within a line segment corresponding to a back side of a second stationary object, among line segments forming a third virtual box corresponding to the second stationary object, or any combination thereof, based on tracking the first reference point in areas divided by grids during frames of a particular section, can detect an error with respect to a position of the host vehicle based on a second position by comparing a first position of the host vehicle and the second position of the host vehicle included in the global positioning system (GPS) information, based on receiving accurate map information including the first position of the host vehicle via the communication circuit, can determine a first width of a road,on which the host vehicle is traveling and which is included in the accurate map information with a second width based on a distance between the first stationary object and the second stationary object based on detecting that the error is less than a reference error, and may detect at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on a difference between the first width and the second width being less than or equal to a first reference width.

[0169] In one example, the processor may not detect at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on the difference between the first width and the second width being greater than the first reference width.

[0170] In one example, the processor may generate a histogram based on an area divided by the grids based on a second axis coordinate of the first reference point tracked on a plane formed by a first axis and the second axis among the first axis, the second axis, and a third axis.

[0171] In one example, the processor may generate the histogram based on the first reference point detected in areas divided by the grids and sub-areas obtained by dividing the areas at a certain interval. The areas divided by the grids may include areas for dividing lanes in which the host vehicle can travel, respectively.

[0172] In one example, the processor may detect at least one of a first coordinate of a second axis of the first reference point, a second coordinate of the second axis of the second reference point, or a third coordinate of the second axis of the third reference point, or any combination thereof, detected on a plane formed by a first axis and the second axis below the first axis, the second axis, and a third axis, and may detect that the first stationary object is farther to the left than the host vehicle based on the first coordinate of the second axis being greater than the second coordinate of the second axis, may detect that the first stationary object is farther to the right than the host vehicle based on the first coordinate of the second axis being less than the second coordinate of the second axis,that the first coordinate of the second axis is greater than the third coordinate of the second axis, detect that the second stationary object is farther to the left than the host vehicle, or can detect that the second stationary object is farther to the right than the host vehicle based on the first coordinate of the second axis being smaller than the third coordinate of the second axis.

[0173] In one example, the processor may recognize the first stationary object as a first road edge based on the fact that a length of the second virtual box is greater than or equal to a first reference length, that virtual boxes, each of which is different from the second virtual box, do not exist in an area where the second virtual box is recognized, that a distance between the second reference point and the host vehicle is less than or equal to a first reference distance, and that the second virtual box includes a certain type of points with a second reference number or more, or may recognize the second stationary object as a second road edge based on the fact that a length of the third virtual box is greater than or equal to the first reference length, that virtual boxes, each of which is different from the third virtual box, do not exist in an area,in which the third virtual box is detected that a distance between the third reference point and the host vehicle is less than or equal to the first reference distance and that the third virtual box includes a certain type of points with the second reference number or more.,

[0174] In one example, the processor may detect the first position and the second position in the grids for dividing a plane formed by a first axis and a second axis among the first axis, the second axis, and a third axis, may detect a first error of a direction of the first axis of the host vehicle based on a first coordinate of the first axis included in the first position and a second coordinate of the first axis included in the second position, may detect a second error of a direction of the second axis of the host vehicle based on a fourth coordinate of the second axis included in the first position and a fifth coordinate of the second axis included in the second position, and may compare the first width to the second width based onthat the first error is smaller than a first reference error and the second error is smaller than a second reference error.,

[0175] In one example, the processor may identify an area in which the host vehicle can travel from areas divided by the grids, and may not identify at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on detecting a stationary object other than at least one of the first stationary object or the second stationary object, or any combination thereof, in an area adjacent to an area in which at least one of the first stationary object or the second stationary object, or any combination thereof, is present.

[0176] In one example, the processor may identify at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on at least one of a length of the second virtual box or a length of the third virtual box, or any combination thereof, being greater than or equal to a second reference length.

[0177] In one example, the processor may detect a first point closest to the host vehicle among points included in the second virtual box, may detect a second point closest to the host vehicle among points included in the third virtual box, and may detect at least one of the first stationary object or the second stationary object, or any combination thereof, as a road edge based on the fact that a difference between a distance between the first point and the second point and a road width included in the accurate map information is less than or equal to a second reference width.

[0178] According to an example of the present disclosure, a vehicle control method may include detecting a first reference point within a line segment corresponding to a rear side of an external vehicle among line segments constituting a first virtual box based on obtaining the first virtual box corresponding to the external vehicle detected by a LiDAR, and removing points located in an area different from an area in which a host vehicle can travel from points obtained by the LiDAR relative to at least one of a second reference point located within a line segment corresponding to a rear side of a first stationary object among line segments constituting a second virtual box corresponding to the first stationary object, or a third reference point located within a line segment,which corresponds to a back side of a second stationary object, is located among line segments forming a third virtual box corresponding to the second stationary object, or any combination thereof, based on tracking the first reference point in areas divided by grids during frames of a particular section, detecting an error with respect to a position of the host vehicle based on a second position by comparing a first position of the host vehicle and the second position of the host vehicle included in GPS information, based on receiving accurate map information including the first position of the host vehicle through a communication circuit, comparing a first width of a road on which the host vehicle is traveling and which is included in the accurate map information,with a second width based on a distance between the first stationary object and the second stationary object based on detecting that the error is less than a reference error, and detecting at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on a difference between the first width and the second width being less than or equal to a first reference width.

[0179] According to one example, the vehicle control method may further include not recognizing at least one of the first stationary object or the second stationary object, or any combination thereof, as a road edge based on the difference between the first width and the second width being greater than the first reference width.

[0180] According to one example, the vehicle control method may further include generating a histogram based on an area divided by the grids based on a coordinate of a second axis of the first reference point traced on a plane formed by a first axis and the second axis among the first axis, the second axis, and a third axis.

[0181] According to one example, the vehicle control method may further include generating the histogram based on the first reference point detected in the areas divided by the grids and the sub-areas obtained by dividing the areas at a certain interval. The areas divided by the grids may include areas for dividing lanes on which the host vehicle can travel, respectively.

[0182] According to one example, the vehicle control method may further comprise detecting at least one of a first coordinate of a second axis of the first reference point, a second coordinate of the second axis of the second reference point, or a third coordinate of the second axis of the third reference point, or any combination thereof, detected on a plane formed by a first axis and the second axis below the first axis, the second axis, and a third axis; detecting that the first stationary object is located further to a left side than the host vehicle based on the first coordinate of the second axis being greater than the second coordinate of the second axis; detecting that the first stationary object is located further to a right side than the host vehicle based on the first coordinate of the second axis being smaller than the second coordinate of the second axis;detecting that the second stationary object is located further to a left side than the host vehicle based on the first coordinate of the second axis being greater than the third coordinate of the second axis, or detecting that the second stationary object is located further to a right side than the host vehicle based on the first coordinate of the second axis being smaller than the third coordinate of the second axis,

[0183] According to one example, the vehicle control method may further include recognizing the first stationary object as a first road edge based on the fact that a length of the second virtual box is greater than or equal to a first reference length, that virtual boxes, each of which is different from the second virtual box, are not present in an area where the second virtual box is recognized, that a distance between the second reference point and the host vehicle is less than or equal to a first reference distance, and the second virtual box includes a certain type of points with a second reference number or more, or recognizing the second stationary object as a second road edge based on the fact that a length of the third virtual box is greater than or equal to the first reference length, that virtual boxes, each of which is different from the third virtual box, are not present in an area,in which the third virtual box is detected that a distance between the third reference point and the host vehicle is less than or equal to the first reference distance and that the third virtual box includes a certain type of points with the second reference number or more.,

[0184] In one example, the vehicle control method may further include detecting the first position and the second position in the grids for dividing a plane formed by a first axis and a second axis among the first axis, the second axis, and a third axis, detecting a first error of a direction of the first axis of the host vehicle based on a first coordinate of the first axis included in the first position and a second coordinate of the first axis included in the second position, detecting a second error of a direction of the second axis of the host vehicle based on a fourth coordinate of the second axis included in the first position and a fifth coordinate of the second axis included in the second position, and comparing the first width with the second width based onthat the first error is smaller than a first reference error and the second error is smaller than a second reference error.,

[0185] According to one example, the vehicle control method may further include detecting an area in which the host vehicle can travel from areas divided by the grids, and not detecting at least one of the first stationary object or the second stationary object or any combination thereof as a road edge based on detecting a stationary object different from at least one of the first stationary object or the second stationary object or any combination thereof in an area adjacent to an area in which at least one of the first stationary object or the second stationary object or any combination thereof exists.

[0186] According to one example, the vehicle control method may further comprise detecting at least one of the first stationary object or the second stationary object, or any combination thereof, as a roadway edge based on at least one of a length of the second virtual box or a length of the third virtual box, or any combination thereof, being greater than or equal to a second reference length.

[0187] According to one example, the vehicle control method may further include detecting a first point closest to the host vehicle among points included in the second virtual box, detecting a second point closest to the host vehicle among points included in the third virtual box, and detecting at least one of the first stationary object or the second stationary object or any combination thereof as a road edge based on the fact that a difference between a distance between the first point and the second point and a road width included in the accurate map information is less than or equal to a second reference width.

[0188] The above description merely illustrates an example of the technical idea of ​​the present disclosure, and various modifications and changes can be made by a person skilled in the art without departing from the characteristics of the present disclosure.

[0189] Accordingly, the examples of the present disclosure are not intended to limit the technical idea of ​​the present disclosure, but to illustrate it, and the scope and spirit of the present disclosure are not limited by the above examples. The scope of the present disclosure should be interpreted by the appended claims, and all equivalents thereof should be construed as being encompassed within the scope of the present disclosure.

[0190] The present technology can detect a road edge using a histogram generated based on tracking a moving object.

[0191] Furthermore, the present technology can detect an area in which a host vehicle can travel by using width information and distance information between virtual boxes included in map information.

[0192] Furthermore, the present technology can reduce the occurrence of errors in a vehicle control system related to the vehicle control device by accurately detecting or identifying a road edge.

[0193] In addition, a variety of effects can be achieved which are understood directly or indirectly through the patent specification.

[0194] Although the present disclosure has been described above with reference to examples and the accompanying drawings, the present disclosure is not limited thereto, but can be modified and altered in various ways by a person skilled in the art to which the present disclosure belongs, without departing from the spirit and scope of the present disclosure as claimed in the following claims. 100 VEHICLE CONTROL DEVICE 110 PROCESSOR 120 LIDAR 130 COMMUNICATION CIRCUIT 201 EXAMPLE 203 EXAMPLE 210 EXTERNAL OBJECT 220 VIRTUAL BOX 301 GRID 303 PARTIAL GRID 310 VIRTUAL BOX 311 REFERENCE POINT 313 POINTS 315 HISTOGRAM 320 VIRTUAL BOX 411 HOST VEHICLE 413 AREA 415 AREA 511 GRIDS 513 AREA 515 VIRTUAL BOX 517 VERTEX 519 VIRTUAL BOX 521 VERTEX 523 EDGE OF ROAD 525 EDGE OF ROAD 1100 PROCESSOR 1300 RAM 1400 User Interface Input Device 1500 User Interface Dispensing Device 1600 STORAGE 1700 NETWORK INTERFACE

Claims

[1] Device comprising: a sensor; a communication circuit; and a processor, wherein the processor is configured to: determine a first reference point within a line segment corresponding to a rear side of an external vehicle, the line segment being one of line segments forming a first virtual box corresponding to the external vehicle detected by the sensor; based on tracking the first reference point in areas divided by grids associated with frames of a particular section, removing points from a plurality of points obtained by the sensor relative to at least one of: a second reference point located within a second line segment corresponding to a backside of a first stationary object, the second line segment being one of line segments forming a second virtual box corresponding to the first stationary object, or a third reference point located within a third line segment corresponding to a back of a second stationary object, the third line segment being one of line segments forming a third virtual box corresponding to the second stationary object, the points being located in an area different from an area where a host vehicle is present; to determine an error with respect to a position of the host vehicle by comparing: a first position of the host vehicle included in the map information received via the communication circuit, and a second position of the host vehicle included in GPS (Global Positioning System) information; based on determining that the error is smaller than a reference error: a first width of a road on which the host vehicle is traveling and which is included in the map information, and compare a second width based on a distance between the first stationary object and the second stationary object; to determine at least one of the first stationary object or the second stationary object as a roadway edge based on a difference between the first width and the second width that is less than or equal to a first reference width; and to issue a signal indicating the edge of the road. [2] The apparatus of claim 1, wherein the processor is configured to: to determine that at least one of the stationary object or the second stationary object is not a roadway edge based on the difference between the first width and the second width being greater than the first reference width. [3] The apparatus of claim 1, wherein the processor is configured to: to generate a histogram based on a range and a second axis coordinate of the first reference point tracked on a plane formed by a first axis and the second axis, wherein: the area is divided by the grids, the first axis corresponds to a direction of travel of the host vehicle, and the second axis is perpendicular to the first axis. [4] The apparatus of claim 3, wherein the processor is configured to: to generate the histogram based on the first reference point detected in the areas divided by the grids and sub-areas obtained by dividing the areas at a certain interval, and wherein the areas divided by the grids include areas for dividing lanes on which the host vehicle can respectively travel. [5] The apparatus of claim 1, wherein the processor is configured to: to determine at least one of: a first coordinate of a second axis of the first reference point, a second coordinate of the second axis of the second reference point or a third coordinate of the second axis of the third reference point, wherein the at least one of the first coordinate, the second coordinate, or the third reference point is detected in a plane formed by a first axis and the second axis perpendicular to the first axis, the first axis corresponding to a direction of travel of the host vehicle; and to determine that the first stationary object is located on a left side of the host vehicle based on the first coordinate of the second axis being greater than the second coordinate of the second axis, to determine that the first stationary object is located on a right side of the host vehicle based on the first coordinate of the second axis being smaller than the second coordinate of the second axis, to determine that the second stationary object is located to the left of the host vehicle based on the first coordinate of the second axis being greater than the third coordinate of the second axis, or to determine that the second stationary object is located on a right side of the host vehicle based on the first coordinate of the second axis being smaller than the third coordinate of the second axis. [6] The apparatus of claim 1, wherein the processor is configured to: to determine the first stationary object as a first road edge on the basis that: a length of the second virtual box is greater than or equal to a first reference length, virtual boxes, each of which is different from the second virtual box, are not located in an area in which the second virtual box is detected, a distance between the second reference point and the host vehicle is less than or equal to a first reference distance, and the second virtual box comprises a specific type of points with a second reference number or more; or to determine the second stationary object as a second road edge on the basis that: a length of the third virtual box is greater than or equal to the first reference length, virtual boxes, each of which is different from the third virtual box, are not located in an area in which the third virtual box is detected, a distance between the third reference point and the host vehicle that is less than or equal to the first reference distance, and the third virtual box contains a specific type of points with the second reference number or more. [7] The apparatus of claim 1, wherein the processor is configured to: to determine the first position and the second position in the grids for dividing a plane formed by a first axis and a second axis, wherein the first axis corresponds to a direction of travel of the host vehicle and the second axis is perpendicular to the first axis; to determine a first error in a direction of the first axis based on: a first coordinate of the first axis included in the first position, and a second coordinate of the first axis included in the second position; to determine a second error in a direction of the second axis of the host vehicle based on: a fourth coordinate of the second axis included in the first position, and a fifth coordinate of the second axis included in the second position; and on the basis that the first error is smaller than a first reference error and the second error is smaller than a second reference error, to compare the first width and the second width. [8] The apparatus of claim 1, wherein the processor is configured to: to determine an area in which the host vehicle can drive from the areas divided by the grids; and to determine that at least one of the first stationary object or the second stationary object is not a roadway edge based on determining a stationary object that is different from at least one of the first stationary object or the second stationary object in an area adjacent to an area in which at least one of the first stationary object or the second stationary object is present. [9] The apparatus of claim 1, wherein the processor is configured to: to determine at least one of the first stationary object or the second stationary object as a roadway edge based on a length of the second virtual box or a length of the third virtual box being greater than or equal to a second reference length. [10] The apparatus of claim 9, wherein the processor is configured to: determine a first point closest to the host vehicle from points encompassed in the second virtual box; to determine a second point closest to the host vehicle from points encompassed in the third virtual box; and to determine at least one of the first stationary object or the second stationary object as a road edge on the basis that: a difference between the distance between the first point and the second point and a road width included in the map information is less than or equal to a second reference width. [11] Method comprising: Determining a first reference point within a line segment corresponding to a rear side of an external vehicle, the line segment being one of line segments forming a first virtual box corresponding to the external vehicle detected by a sensor; Removing, based on tracking the first reference point in areas divided by grids associated with frames of a particular section, points from a plurality of points obtained by the sensor relative to at least one of: a second reference point located within a second line segment corresponding to a back of a first stationary object, the second line segment being one of the line segments forming a second virtual box corresponding to the first stationary object, or a third reference point located within a third line segment corresponding to a backside of a second stationary object, the third line segment being one of the line segments forming a third virtual box corresponding to the second stationary object; Determining an error related to a host vehicle position by comparing: a first position of the host vehicle included in map information received via a communication circuit, and a second position of the host vehicle included in GPS information; based on determining that the error is smaller than a reference error, compare: a first width of a road on which the host vehicle is traveling and which is included in the map information, and a second width based on a distance between the first stationary object and the second stationary object; Determining at least one of the first stationary object or the second stationary object as a roadway edge based on a difference between the first width and the second width being less than or equal to a first reference width; and Issuing a signal indicating the edge of the road. [12] The method of claim 11, further comprising: Determining that at least one of the first stationary object or the second stationary object is not a roadway edge based on the difference between the first width and the second width being greater than the first reference width. [13] The method of claim 11, further comprising: Generating a histogram based on a range and a second axis coordinate of the first reference point tracked on a plane formed by a first axis and the second axis, wherein: the area is divided by the grids, the first axis corresponds to a direction of travel of the host vehicle, and the second axis is perpendicular to the first axis. [14] The method of claim 13, further comprising: Generating the histogram based on the first reference point detected in the areas divided by the grids and sub-areas obtained by dividing the areas at a certain interval, and wherein the areas divided by the grids include areas for dividing lanes on which the host vehicle can respectively travel. [15] The method of claim 11, further comprising: Determine at least one of: a first coordinate of a second axis of the first reference point, a second coordinate of the second axis of the second reference point or a third coordinate of the second axis of the third reference point, wherein the at least one of the first coordinate, the second coordinate, or the third reference point is detected in a plane formed by a first axis and the second axis perpendicular to the first axis, the first axis corresponding to a direction of travel of the host vehicle; and Determining that the first stationary object is located on a left side of the host vehicle based on the first coordinate of the second axis being greater than the second coordinate of the second axis; Determining that the first stationary object is located on a right side of the host vehicle based on the first coordinate of the second axis being less than the second coordinate of the second axis; Determining that the second stationary vehicle is located on a left side of the host vehicle based on the first coordinate of the second axis being greater than the third coordinate of the second axis; or Determining that the second stationary object is located on a right side of the host vehicle based on the first coordinate of the second axis being less than the third coordinate of the second axis. [16] The method of claim 11, further comprising: Determining the first stationary object as a first roadway edge based on: a length of the second virtual box is greater than or equal to a first reference length, virtual boxes, each of which is different from the second virtual box, are not present in an area in which the second virtual box is detected, a distance between the second reference point and the host vehicle is less than or equal to a first reference distance, and the second virtual box comprises a specific type of points with a second reference number or more; or Determining the second stationary object as a second roadway edge based on: a length of the third virtual box is greater than or equal to the first reference length, virtual boxes, each of which is different from the third virtual box, do not exist in an area in which the third virtual box is detected, a distance between the third reference point and the host vehicle that is less than or equal to the first reference distance, and the third virtual box contains a specific type of points with the second reference number or more. [17] The method of claim 11, further comprising: Determining the first position and the second position in the grids for dividing a plane formed by a first axis and a second axis, wherein the first axis corresponds to a direction of travel of the host vehicle and the second axis is perpendicular to the first axis; Determining a first error in a direction of the first axis based on: a first coordinate of the first axis included in the first position, and a second coordinate of the first axis included in the second position; Determining a second error in a direction of the second axis of the host vehicle based on: a fourth coordinate of the second axis included in the first position, and a fifth coordinate of the second axis included in the second position; and Comparing on the basis that the first error is smaller than a first reference error and the second error is smaller than a second reference error, the first width and the second width. [18] The method of claim 11, further comprising: Determining an area in which the host vehicle can travel from the areas divided by the grids; and Determining that at least one of the first stationary object or the second stationary object is not a roadway edge based on determining a stationary object that is different from at least one of the first stationary object or the second stationary object in an area adjacent to an area in which at least one of the first stationary object is present. [19] The method of claim 11, further comprising: Determining at least one of the first stationary object or the second stationary object as a roadway edge based on a length of the second virtual box or a length of the third virtual box being greater than or equal to a second reference length. [20] The method of claim 19, further comprising: Determining a first point closest to the host vehicle from points included in the second virtual box; Determining a second point closest to the host vehicle from the points encompassed in the third virtual box; and Determining at least one of the first stationary object or the second stationary object as a roadway edge based on: a difference between the distance between the first point and the second point and a road width included in the map information is less than or equal to a second reference width.

Images