VEHICLE CONTROL DEVICE AND METHOD THEREFOR

Abstract

A vehicle control device (100) may include a LiDAR (120) and a processor (110). According to a method, the processor (110) may acquire a plurality of LiDAR data points by removing points of a certain height or higher from a point cloud belonging to an external vehicle, may generate a bounding box based on contour points indicating an outer perimeter of the external vehicle, and may acquire a final bounding box obtained by correcting the bounding box based on an angle between a first traveling direction of a virtual box and a second traveling direction of the bounding box exceeding a reference angle and based on a distance between a first position of the virtual box and a second position of the bounding box being less than or equal to a first reference distance.

Description

Technical field

[0001] The present disclosure and invention relates to a vehicle device and a method for identifying an external object using LiDAR (LiDAR = “Light Detection and Ranging”). background

[0002] Numerous researches are being conducted to detect an external object using numerous sensors to assist in driving a vehicle.

[0003] In particular, the external object can be identified using a LiDAR while the vehicle is driving in a driver assistance device activation mode or in an autonomous driving mode.

[0004] When an external vehicle is identified using the LiDAR, a virtual box may be generated to include the external vehicle and a side mirror of the external vehicle, and a traveling direction of the virtual box may be identified using the virtual box including the side mirror. When the traveling direction of the virtual box is identified using the virtual box including the side mirror, the traveling direction of the virtual box may be misidentified due to the side mirror, and consequently, the external vehicle imaged by the virtual box may be identified as merging (e.g., merging into the own lane or intersecting the own travel path).

[0005] If it is detected that the external vehicle represented by the virtual box is merging, the vehicle's route can be changed or the vehicle's speed can be reduced. To correct errors in a vehicle control system with a vehicle control device, the vehicle's route can be changed or the vehicle's speed can be reduced. Short explanation

[0006] The present disclosure or invention (hereinafter also referred to as disclosure) relates to a device for controlling a vehicle and a related method, and more particularly relates to a technology for identifying an external object using LiDAR.

[0007] Some embodiments of the present disclosure can solve the above-mentioned problems of the prior art while maintaining the advantages achieved by the prior art.

[0008] An embodiment of the present disclosure provides a vehicle control device that generates a bounding box obtained by omitting a portion corresponding to a side mirror of an external vehicle, and a method thereof.

[0009] An embodiment of the present disclosure provides a vehicle control device that precisely identifies a traveling direction of the external vehicle by generating the bounding box obtained by omitting or excluding the portion corresponding to the side mirror of the external vehicle, and a method thereof.

[0010] An embodiment of the present disclosure provides a vehicle control device that accurately identifies the type of the external vehicle using information including the side mirror even when the bounding box obtained by excluding the portion corresponding to the side mirror of the external vehicle is generated, and a method thereof.

[0011] Technical problems to be solved by some embodiments of the present disclosure are not necessarily limited to the above-mentioned problems, and some embodiments can solve other technical problems not mentioned here, which can be clearly understood by those skilled in the art to which the present disclosure belongs from the following description.

[0012] According to one embodiment of the present disclosure, a vehicle control device may include a LiDAR (Light Detection and Ranging) and a processor. The processor may acquire a plurality of points by extracting points with a certain height or higher (e.g., a certain height or a height higher than the certain height) from a point cloud based on the acquisition of the point cloud belonging to an external vehicle (e.g.,corresponding thereto) are removed by the LiDAR, may generate a bounding box based on contour points indicating an outer perimeter of the external vehicle among the plurality of points, and may obtain a final bounding box obtained by correcting the bounding box based on the fact that an angle between a first traveling direction of a virtual box through the point cloud and a second traveling direction of the bounding box exceeds a reference angle and a distance between a first position of the virtual box corresponding to (e.g., belongs to or corresponds to) a center of a rear surface of the external vehicle and a second position of the bounding box corresponding to (e.g., belongs to or corresponds to) the center of the rear surface of the external vehicle is less than or equal to a first reference distance.

[0013] In one embodiment, the processor may remove the points with the determined height or higher from the point cloud corresponding to the external vehicle based on (e.g., if / in case that) a distance between a vehicle and the external vehicle is less than or equal to a second reference distance.

[0014] In one embodiment, the determined height may include a first determined height and a second determined height that exceeds the first determined height. The processor may identify a length of the point cloud in a direction of a first axis below the first axis, a second axis, and a third axis, may remove first points identified at the first determined height or higher in a direction of the third axis based on (e.g., if / in case that) the length of the point cloud is within a first range, and may remove second points identified at the second determined height or higher in a direction of the third axis based on (e.g., if / in case that) the length of the point cloud is within a second range that is greater than the first range.

[0015] In one embodiment, the processor may identify the contour points on each of a plurality of planes formed in a third axis direction among a first axis, a second axis, and the third axis, and may generate the bounding box comprising the contour points identified on each of the plurality of planes.

[0016] In one embodiment, the processor may identify an arrangement (e.g., a row, an array, and / or the like) of the contour points based on a position at which the point cloud is identified, and may identify a first line segment of the bounding box corresponding to a side surface of the external vehicle based on the position at which the point cloud is identified and the arrangement of the contour points.

[0017] In one embodiment, the processor may identify a first endpoint and a second endpoint that are not connected to other contour points among the contour points, may identify a peak point that is farthest from a line segment connecting the first endpoint and the second endpoint, may identify a second line segment connecting the peak point and an endpoint included in contour points belonging to a side surface of the external vehicle among the first endpoint and the second endpoint, and may identify representative points belonging to the side surface of the external vehicle in a region that is different from a region between the first line segment and the second line segment (e.g., at least partially).

[0018] In one embodiment, the processor may obtain a lateral position correction value of the bounding box based on a distance between the first line segment and an average of coordinate values ​​of the representative points in a second axis direction among a first axis, the second axis, and a third axis, and may obtain the final bounding box based on (e.g., if / in case that) a difference between the lateral position correction value and a reference value is less than a threshold.

[0019] In one embodiment, the processor may identify a representative intermediate point among the representative points, may identify a first representative point and a second representative point that are included within a certain distance from the representative intermediate point and that are located farthest from the representative intermediate point in distance, may identify the second traveling direction based on the first representative point and the second representative point, and may obtain the final bounding box based on a difference between the first traveling direction and the second traveling direction exceeding the reference angle.

[0020] In one embodiment, the processor may assign a first identifier to the virtual box by the point cloud and may assign a second identifier to the final bounding box indicating that the final bounding box is generated by the virtual box to which the first identifier is assigned.

[0021] In one embodiment, the processor may identify a type of the external vehicle based on the virtual box to which the first identifier is assigned, and may track (e.g., monitor) a travel route of the external vehicle based on the final bounding box to which the second identifier is assigned.

[0022] According to an embodiment of the present disclosure, a vehicle control method may include: acquiring a plurality of points by removing points with a certain height or higher from a point cloud based on acquiring the point cloud belonging to an external vehicle by a LiDAR, generating a bounding box based on contour points indicating an outer periphery of the external vehicle among the plurality of points, and obtaining a final bounding box obtained by correcting the bounding box based on a condition that an angle between a first traveling direction of a virtual box through the point cloud and a second traveling direction of the bounding box exceeds a reference angle and a distance between a first position of the virtual box corresponding to a center of a rear surface of the external vehicle and a second position of the bounding box,which corresponds to the center of the rear surface of the external vehicle, is less than or equal to a first reference distance.

[0023] According to an embodiment, the vehicle control method may further comprise: removing the points with the determined height or higher from the point cloud belonging to the external vehicle based on (eg, if / in case that) a distance between a vehicle and the external vehicle is less than or equal to a second reference distance.

[0024] In one embodiment, the determined height may include a first determined height and a second determined height that exceeds the first determined height. The vehicle control method may further comprise: identifying a length of the point cloud in a direction of a first axis among the first axis, a second axis, and a third axis, removing first points identified at the first determined height or higher in a direction of the third axis based on (e.g., if / in case that) the length of the point cloud is within a first range, and removing second points identified at the second determined height or higher in a direction of the third axis based on (e.g., if / in case that) the length of the point cloud is within a second range that is greater than the first range.

[0025] According to one embodiment, the vehicle control method may further comprise: identifying the contour points on each of a plurality of planes formed in a direction of a third axis among a first axis, a second axis, and the third axis, and generating the bounding box including the contour points identified on each of the plurality of planes.

[0026] According to one embodiment, the vehicle control method may further comprise: identifying an arrangement of the contour points based on a position at which the point cloud is identified, and identifying a first line segment of the bounding box corresponding to a side surface of the external vehicle based on the position at which the point cloud is identified and the arrangement of the contour points.

[0027] According to an embodiment, the vehicle control method may further comprise: identifying a first end point and a second end point, which are not connected to other contour points, among the contour points, identifying a peak point which is farthest from a line segment connecting the first end point and the second end point, identifying a second line segment connecting the peak point and an end point included in contour points belonging to the side surface of the external vehicle from (e.g., from / below) the first end point and the second end point, and identifying representative points belonging to the side surface of the external vehicle in a range which is different from a range between the first line segment and the second line segment (e.g., at least partially).

[0028] According to an embodiment, the vehicle control method may further comprise: obtaining a lateral position correction value of the bounding box based on a distance between the first line segment and an average of coordinate values ​​of the representative points in a second axis direction among a first axis, the second axis, and a third axis, and obtaining the final bounding box based on (e.g., if / in case that) a difference between the lateral position correction value and a reference value is smaller than a threshold.

[0029] According to an embodiment, the vehicle control method may further comprise: identifying a representative intermediate point among the representative points, identifying a first representative point and a second representative point which are included within a certain distance from the representative intermediate point and which are located farthest from the representative intermediate point in distance, among the representative points, identifying the second traveling direction based on the first representative point and the second representative point, and obtaining the final bounding box based on a difference between the first traveling direction and the second traveling direction exceeding the reference angle.

[0030] According to one embodiment, the vehicle control method may further comprise: assigning a first identifier to the virtual box by the point cloud, and assigning, to the final bounding box, a second identifier indicating that the final bounding box is generated by the virtual box to which the first identifier is assigned.

[0031] According to one embodiment, the vehicle control method may further comprise: identifying a type of the external vehicle based on the virtual box to which the first identifier is assigned, and tracking a travel route of the external vehicle based on the final bounding box to which the second identifier is assigned. Short description of the drawings

[0032] 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 embodiment of the present disclosure, Fig. 2 is a diagram showing an example of comparing an angle between a first traveling direction of a virtual box and a second traveling direction of a bounding box according to an embodiment of the present disclosure, Fig. 3A is a diagram showing an example of removing points depending on a position of an external vehicle according to an embodiment of the present disclosure, Fig. 3B is a diagram showing an example of removing points depending on a distance between a vehicle and an external vehicle according to an embodiment of the present disclosure, Fig. 3C is a diagram showing an example of removing points depending on a type of an external vehicle according to an embodiment of the present disclosure, Fig. 4 is a diagram showing an example of a vehicle control device that removes points having a certain height or higher according to an embodiment of the present disclosure, Fig. 5 is a diagram showing an example of identifying a line segment of a bounding box corresponding to a side surface of the external vehicle based on an arrangement of contour points according to an embodiment of the present disclosure, Fig. 6 is a diagram showing an example of identifying representative points representing a side surface of an external vehicle according to an embodiment of the present disclosure, Fig. 7 is a diagram showing an example of determining whether to generate a final bounding box based on a lateral position of a bounding box in one embodiment of the present disclosure, Fig. 8 is a diagram showing an example of identifying a traveling direction based on representative points according to an embodiment of the present disclosure, Fig. 9 is a diagram showing an example of using a virtual box and a bounding box according to an embodiment of the present disclosure, Fig. 10 is a diagram showing an example of a flowchart related to a vehicle control method according to an embodiment of the present disclosure, Fig. 11 is a diagram showing an example of a result of applying an embodiment of the present disclosure, and Fig. 12 is a diagram showing a data processing system associated with a vehicle control apparatus or a vehicle control method according to an embodiment of the present disclosure. Detailed description of exemplary embodiments

[0033] Hereinafter, some exemplary embodiments of the present disclosure will be described in detail with reference to the exemplary drawings. When adding reference numerals to the components of each drawing, it should be noted that an identical or equivalent component will be designated by the identical reference numeral even if they are shown in other drawings. Furthermore, in describing some exemplary embodiments of the present disclosure, detailed descriptions relating to well-known functions or structures will be omitted if they might unnecessarily obscure the subject matter of the present disclosure.

[0034] When describing components of exemplary embodiments of the present disclosure, the terms "first," "second," "A," "B," "(a)," "(b)," and the like may be used. These terms are used only to distinguish one component from another component, but do not limit the corresponding components regardless of the order or ranking of the corresponding components. Unless otherwise defined, all terms used herein, including technical and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs. It is to be understood that the terms used herein should be interpreted to have a meaning consistent with their meaning in the context of the present disclosure and the relevant art.

[0035] In the following, numerous embodiments of the present disclosure are described with reference to the Fig. 1 to 12 described in detail.

[0036] Fig. 1 shows an example of a block diagram of a vehicle control device according to an embodiment of the present disclosure.

[0037] With reference to Fig. 1, a vehicle control device 100 according to an embodiment of the present disclosure may be implemented inside or outside a vehicle (e.g., a host vehicle or subject vehicle, respectively), and some of the components included in the vehicle control device 100 may be implemented inside or outside the vehicle. For example, the vehicle control device 100 may be integrated into the internal control units of a vehicle and / or may be implemented with a separate device connected to the control units of the vehicle via a separate connection. For example, the vehicle control device 100 may also further include components included in Fig. 1 are not shown.

[0038] A vehicle control device 100 according to one embodiment may include a processor 110 and a LiDAR (or LiDAR device, where LiDAR = "Light Detection and Ranging") 120, one or both of which may be present in a plurality or may include multiple components thereof. The processor 110 or the LiDAR 120 may be electrically and / or operatively (e.g., operationally or functionally) connected to each other by an electronic component having a communication bus.

[0039] Hereinafter, the operatively connected hardware parts may have a direct and / or indirect connection between the hardware parts by being connected wired and / or wirelessly, so that a second hardware can be controlled by the first hardware among the hardware parts.

[0040] Although various blocks are shown, an embodiment is not necessarily limited to these. Some of the Fig. 1 may be included in a single integrated circuit, including a system-on-a-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 shown hardware parts.

[0041] A vehicle control device 100 according to an embodiment may include hardware for processing data based on one or more instructions. The data processing hardware may include the processor 110. For example, the data processing hardware may include 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, for example, a dual-core, a quad-core, a hexa-core, or an octa-core.

[0042] The LiDAR 120 provided in the vehicle control device 100 according to an embodiment can obtain data sets from the identification of objects surrounding the vehicle control device 100 (e.g., the vehicle equipped therewith). For example, the LiDAR 120 can identify at least one of a position of the surrounding object, a direction of movement of the surrounding object, a speed of the surrounding object, or any combination thereof based on a pulsed laser signal emitted by the LiDAR 120 and reflected and retransmitted by the surrounding object.

[0043] For example, the LiDAR 120 may acquire data sets to express or represent an external object in the space defined by a first axis, a second axis, and a third axis based on a pulsed laser signal reflected from surrounding objects. For example, each of the data sets may correspond to a respective frame.

[0044] The first axis may, for example, have or be an x-axis. The second axis may, for example, have or be a y-axis. The third axis may, for example, have or be a z-axis. The first axis, the second axis, and the third axis may, for example, be perpendicular to each other and intersect based on an origin point. The first axis, the second axis, and the third axis are not limited to the examples above. For simplicity, the first axis is referred to as the x-axis, the second axis as the y-axis, and the third axis as the z-axis.

[0045] For example, the LiDAR 120 may acquire data sets comprising a plurality of points in space formed by the x-axis, the y-axis, and the z-axis based on the reception of the pulse laser signal with a certain period.

[0046] The processor 110, which is provided in the vehicle control device 100 according to an embodiment, can emit light from a vehicle using the LiDAR 120. For example, the LiDAR 120 can receive light emitted by the vehicle. For example, the processor 110 can identify at least one of a position, a speed, a direction of movement, or any combination thereof of a surrounding object based on a time it takes to emit light emitted by the vehicle and / or a time it takes to receive light emitted by the vehicle.

[0047] For example, the processor 110 may acquire data sets including a plurality of points based on the time required to transmit light emitted by the vehicle and the time required to receive light emitted by the vehicle. The processor 110 may acquire data sets expressing a plurality of points in a three-dimensional virtual coordinate system including the x-axis, the y-axis, and the z-axis.

[0048] In one embodiment, the processor 110 may acquire a point cloud associated with an external vehicle (e.g., one or more surrounding vehicles in the vicinity of the host vehicle or subject vehicle having the LiDAR) through the LiDAR 120. For example, a point cloud may be obtained by performing grouping (also called clustering) based on each of the plurality of points acquired by the LiDAR 120 being identified at a particular (e.g., predetermined or specific) distance. For example, each of the plurality of points identified at the particular distance may have a distance between the plurality of points that is smaller than the predetermined distance.

[0049] For example, a point cloud may have a set of points for creating a virtual box representing an external object for identifying contour points.

[0050] In one embodiment, the processor 110 may remove points having a certain (e.g., predetermined or specific) height or higher (i.e., e.g., a certain height or a height higher than the certain height) from a point cloud based on the LiDAR 120 acquiring the point cloud associated with an external vehicle. For example, based on the LiDAR 120 acquiring the point cloud, the processor 110 may acquire the plurality of points based on removing points having a certain height or higher from the point cloud.

[0051] For example, the processor 110 may acquire the plurality of points by removing points with a certain height or higher from the point cloud based on the acquisition of the point cloud corresponding to the external vehicle traveling in a lane other than a lane in which a vehicle is traveling by the LiDAR 120.

[0052] In one embodiment, processor 110 may identify the contour points indicating an outer perimeter (e.g., an outer contour, an outline) of the external vehicle from the plurality of points. For example, the contour points may be identified on each of the planes formed by the x-axis, the y-axis, and the z-axis based on the z-axis.

[0053] For example, the contour points may be obtained based on representative points included in the point cloud on each of the planes formed from the x-axis, the y-axis, and the z-axis based on the z-axis. For example, the representative points may include all and / or part of points located on the outer side of a plurality of points included in the point cloud. For example, the point cloud may be obtained by performing clustering based on identifying that a distance between the plurality of points acquired by the LiDAR 120 is within a certain distance.

[0054] In one embodiment, processor 110 may generate a bounding box (e.g., a bounding box, bounding box, or the like) based on contour points indicating the outer perimeter of the external vehicle among the plurality of points. For example, the bounding box may include an external vehicle within a frame.

[0055] In one embodiment, processor 110 may identify a first direction of travel (also, e.g., first heading direction) of a virtual box through the point cloud. Processor 110 may identify a second direction of travel (also, e.g., second heading direction) of a bounding box. Processor 110 may determine whether an angle between the first direction of travel of the virtual box and the second direction of travel of the bounding box through the point cloud is less than or equal to a reference angle.

[0056] In one embodiment, the processor 110 may identify a first position of the virtual box that corresponds to (e.g., belongs to or corresponds to) a center of a rear surface of the external vehicle. The processor 110 may identify a second position of the bounding box that corresponds to (e.g., belongs to or corresponds to) a center of a rear surface of the external vehicle. For example, the processor 110 may determine a distance between the first position of the virtual box that corresponds to the center of the rear surface of the external vehicle and the second position of the bounding box that corresponds to the center of the rear surface of the external vehicle. For example, the processor 110 may determine whether the distance (e.g., the distance) between the first position and the second position is less than or equal to a first reference distance.

[0057] In one embodiment, the processor 110 may obtain a final bounding box, which is obtained by correcting the bounding box, based on (i.e., e.g., if / in the event that - hereinafter also partly only: based on) the angle between the first direction of travel of the virtual box through the point cloud and the second direction of travel of the bounding box exceeds the reference angle and that the distance between the first position of the virtual box, which corresponds to the center of the rear surface of the external vehicle, and the second position of the bounding box, which corresponds to the center of the rear surface of the external vehicle, is less than or equal to the first reference distance.

[0058] In one embodiment, the processor 110 may remove points with a certain height or higher from the point cloud belonging to the external vehicle based on the distance between the vehicle (e.g., the host vehicle or subject vehicle) and the external vehicle being less than or equal to a second reference distance. For example, the processor 110 may identify a distance between a line segment belonging to the front surface of the vehicle and a line segment belonging to the rear surface of the external vehicle. The processor 110 may remove points with a certain height or higher from the point cloud belonging to the external vehicle based on the distance between the vehicle (e.g.,if / in case that) the distance between the line segment belonging to the front surface of the vehicle and the line segment belonging to the rear surface of the external vehicle is less than or equal to the second reference distance.

[0059] For example, the points with the specified height or higher may include points corresponding to the side view mirror of the external vehicle. Processor 110 may precisely identify the direction of travel of the virtual box, the bounding box, and / or the final bounding box corresponding to the external vehicle by removing points corresponding to the side view mirror of the external vehicle.

[0060] In one embodiment, the processor 110 may obtain the bounding box by removing points of a certain height or higher from the point cloud corresponding to the external vehicle based on (e.g., if / in case) the distance between the line segment corresponding to the front surface of the vehicle and the line segment corresponding to the rear surface of the external vehicle being less than or equal to the second reference distance.

[0061] In one embodiment, processor 110 may identify a length of the point cloud in a first-axis direction among the first axis, the second axis, and the third axis. For example, the first axis may include or be the x-axis. The second axis may include or be the y-axis. The third axis may include or be the z-axis.

[0062] For example, the specific height may include a first specific height and / or a second specific height. The second specific height may, for example, exceed the first specific height (e.g., be greater than the first specific height).

[0063] In one embodiment, the processor 110 may remove first points identified at the first determined height or higher in the third-axis direction based on (e.g., if / in case) the length of the point cloud is within a first range.

[0064] In one embodiment, the processor 110 may remove second points identified at the second determined height or higher in the third-axis direction based on (e.g., if / in case) the length of the point cloud is within a second range that is larger than the first range.

[0065] For example, the length of the point cloud being within the first range may indicate a case where the external vehicle is a passenger vehicle. For example, the length of the point cloud being within the second range may indicate a case where the external vehicle is a large vehicle, including at least one of a truck, a bus, or any combination thereof.

[0066] In one embodiment, processor 110 may identify contour points on each of a plurality of planes defined by the third-axis direction, the first-axis direction, the second-axis direction, and the third-axis direction. Processor 110 may generate a bounding box comprising the contour points identified on each of the plurality of planes.

[0067] In one embodiment, processor 110 may identify an arrangement (e.g., a row, an array, and / or the like) of contour points based on the position at which the point cloud is identified. Processor 110 may identify a first line segment of the bounding box corresponding to a side surface of the external vehicle based on a position at which the point cloud is identified and / or the arrangement of contour points.

[0068] In one embodiment, processor 110 may identify a first endpoint and / or a second endpoint that is not connected to other contour points among the contour points. Processor 110 may identify a peak point (e.g., also called a vertex or "peak point") that is farthest from the line segment connecting the first endpoint and the second endpoint.

[0069] The processor 110 may identify a second line segment connecting the peak point and an end point included in the contour points belonging to the side surface of the external vehicle among the first end point and the second end point. The processor 110 may identify representative points belonging to the side surface of the external vehicle in a region that differs (e.g., at least partially) from a region between the first line segment and the second line segment.

[0070] In one embodiment, the processor 110 may obtain the average of the coordinate values ​​of the representative points in a second-axis direction from the first axis, the second axis, and the third axis. The processor 110 may obtain a lateral position correction value of the bounding box based on a distance between the first line segment and the average of the coordinate values ​​of the representative points in the second-axis direction from the first axis, the second axis, and the third axis.

[0071] The processor 110 may obtain a final bounding box obtained by correcting the bounding box based on (e.g., if) a difference between the lateral position correction value and the reference value being smaller than a threshold.

[0072] In one embodiment, the processor 110 may identify an intermediate representative point (e.g., an intermediate representative point) among the representative points. The processor 110 may identify a first representative point and a second representative point that are farthest from the intermediate representative point among the representative points that are within a certain distance. The processor 110 may identify the second direction of travel of the bounding box based on the first representative point and the second representative point. For example, the processor 110 may identify the second direction of travel of the bounding box based on a direction extending from the first representative point to the second representative point.

[0073] The processor 110 may obtain a final bounding box obtained by correcting the bounding box based on a difference between the first traveling direction of the virtual box and the second traveling direction of the bounding box exceeding the reference angle.

[0074] In one embodiment, processor 110 may assign a first identifier to the virtual box from the point cloud. Processor 110 may assign a second identifier to the final bounding box, indicating that the final bounding box is generated based on the virtual box assigned the first identifier.

[0075] In one embodiment, processor 110 may identify the type of external vehicle based on the virtual box to which the first identifier is assigned. Processor 110 may track (e.g., monitor) the travel route of the external vehicle based on the final bounding box to which the second identifier is assigned.

[0076] In one embodiment, processor 110 may output the virtual box and the final bounding box. For example, processor 110 may output the virtual box and the final bounding box generated from the point cloud of the external vehicle. For example, processor 110 may assist in operating the vehicle including vehicle control device 100 based on the final bounding box and the virtual box obtained from the point cloud associated with the external vehicle.

[0077] Fig. 2 shows an example of comparing an angle between a first direction of travel of a virtual box and a second direction of travel of a bounding box according to an embodiment of the present disclosure.

[0078] With reference to Fig. 2, a processor (e.g., processor 110 in Fig. 1) a vehicle control device (e.g., the vehicle control device 100 in Fig. 1) according to one embodiment, a virtual box 211 belonging to an external vehicle is represented by a LiDAR (e.g., the LiDAR 120 in Fig. 1). For example, the virtual box 211 may be generated from a plurality of points based on a point cloud belonging to the external vehicle.

[0079] In one embodiment, the processor may identify a first direction of travel 213 of the virtual box 211. For example, the first direction of travel 213 of the virtual box 211 may be formed as a direction from a center of a rear surface (e.g., a rear surface) of the external vehicle to a front surface (e.g., a front surface) of the external vehicle.

[0080] In one embodiment, the processor may generate a bounding box 221. For example, the processor may generate the bounding box 221 based on removing points with a certain elevation or higher (e.g., a certain elevation or an elevation higher than the certain elevation) from the point cloud. The processor may identify a second direction of travel 223 within the bounding box 221.

[0081] In one embodiment, the processor may identify an angle 231 between the first direction of travel 213 of the virtual box 211 and the second direction of travel 223 of the bounding box 221. The processor may obtain a final bounding box, which may be obtained by correcting the bounding box 221, based on the angle 231 between the first direction of travel 213 of the virtual box 211 and the second direction of travel 223 of the bounding box 221 exceeding a reference angle.

[0082] As described above, according to one embodiment, the processor of the vehicle control device may obtain the final bounding box representing the external vehicle by obtaining the final bounding box based on the angle 231 between the first traveling direction 213 of the virtual box 211 and the second traveling direction 223 of the bounding box 221.

[0083] Fig. 3A shows an example of removing points depending on a position of an external vehicle in one embodiment of the present disclosure.

[0084] With reference to Fig. 3A, a processor (e.g., processor 110 in Fig. 1) a vehicle control device (e.g., the vehicle control device 100 in Fig. 1) Identify a lateral position of an external vehicle, according to one embodiment. For example, the processor may identify the lateral position of the external vehicle based on vehicle 311.

[0085] The processor can determine the lateral position of the external vehicle based on a point cloud belonging to the external vehicle and detected by a LiDAR (e.g. the LiDAR 120 in Fig. 1) was obtained.

[0086] For example, the processor may identify a coordinate value of the point cloud corresponding to an external vehicle 321. The processor may identify an intermediate value of a y-axis direction among the coordinate values ​​of the point cloud corresponding to the external vehicle 321. For example, the processor may perform operations to remove points corresponding to a side view mirror of the external vehicle 321 based on the intermediate value of the y-axis direction among the coordinate values ​​of the point cloud corresponding to the external vehicle 321 being smaller than a coordinate range corresponding to a road on which the vehicle (e.g., the host vehicle or subject vehicle) 311 is traveling.For example, the operation of removing points corresponding to the side mirror of the external vehicle 321 may include an operation of removing points with a certain height or higher from the point cloud corresponding to the external vehicle 321.

[0087] For example, the processor may identify a coordinate value of the point cloud corresponding to an external vehicle 323. The processor may identify an intermediate value of a y-axis direction among the coordinate values ​​of the point cloud corresponding to the external vehicle 323. For example, the processor may perform operations to remove points corresponding to a side view mirror of the external vehicle 323 based on the intermediate value of the y-axis direction among the coordinate values ​​of the point cloud corresponding to the external vehicle 323 being larger than a coordinate range corresponding to a road on which the vehicle 323 is traveling. For example, the operation of removing points corresponding to the side view mirror of the external vehicle 323 may include an operation of removing points with a certain height or higher from the point cloud corresponding to the external vehicle 323.

[0088] As described above, the processor of the vehicle control device according to one embodiment may not perform an operation for removing points belonging to the side mirror of the external vehicle identified on all roads, but may remove points belonging to the side mirror of the external vehicle (e.g., the external vehicle 321 and / or the external vehicle 323) traveling on a road other than a road on which the vehicle (e.g., the host vehicle or subject vehicle) is traveling, thereby reducing the load on the processor.

[0089] Fig. 3B shows an example of removing points depending on a distance between a vehicle and an external vehicle in one embodiment of the present disclosure.

[0090] Referring to Fig. 3B, a processor (e.g., processor 110 in Fig. 1) a vehicle control device (e.g., the vehicle control device 100 in Fig. 1) according to one embodiment, a distance between a vehicle (e.g., a host vehicle or subject vehicle) 331 and an external vehicle (e.g., an external vehicle 341 and / or an external vehicle 343) based on a plurality of points detected by a LiDAR (e.g., the LiDAR 120 in Fig. 1) were obtained.

[0091] In one embodiment, the processor may identify a line segment that includes a center of a rear surface of the external vehicle 341 and is parallel to a y-axis. The processor may identify a distance 333 between a line segment that includes the center of the rear surface of the external vehicle 341 and is parallel to the y-axis and a line segment that corresponds to (e.g., belongs to or corresponds to) a front surface of the vehicle 331.

[0092] In one embodiment, the processor may remove points of a certain height or higher from a point cloud corresponding to the external vehicle 341 based on the distance 333 between the line segment comprising the center of the rear surface of the external vehicle 341 and being parallel to the y-axis and the line segment corresponding to the front surface of the vehicle 331 being less than or equal to a reference distance 335.

[0093] In one embodiment, the processor may identify a line segment that includes a center of a rear surface of the external vehicle 343 and is parallel to a y-axis. The processor may identify a distance 337 between a line segment that includes the center of the rear surface of the external vehicle 343 and is parallel to the y-axis and a line segment that corresponds to (e.g., belongs to or corresponds to) a front surface of the vehicle 331.

[0094] In one embodiment, the processor may identify a line segment that includes the center of a rear surface of the external vehicle 343 and is parallel to a y-axis. The processor may generate a virtual box and / or a bounding box using a point cloud associated with the external vehicle 343 based on the distance 337 between the line segment that includes the center of the rear surface of the external vehicle 343 and is parallel to the y-axis and the line segment corresponding to the front surface of the vehicle 331 exceeding the reference distance 335.

[0095] As mentioned above, according to one embodiment, the processor of the vehicle control device may remove points corresponding to the side view mirror of the external vehicle based on the distance between the vehicle 331 and the external vehicle (e.g., the external vehicle 341 and / or the external vehicle 343). The processor may remove points corresponding to the side view mirror of the external vehicle based on the distance between the vehicle 331 and the external vehicle (e.g., the external vehicle 341 and / or the external vehicle 343), thereby reducing the load on the processor.

[0096] Fig. 3C shows an example of removing points depending on a type of external vehicle in one embodiment of the present disclosure.

[0097] With reference to Fig. 3C, a processor (e.g., processor 110 in Fig. 1) a vehicle control device (e.g., the vehicle control device 100 in Fig. 1) according to one embodiment, a length of a point cloud belonging to an external vehicle (e.g., an external vehicle 361 and / or an external vehicle 371) using LiDAR (e.g., the LiDAR 120 in Fig. 1). The vehicle control device is contained in the vehicle 351.

[0098] For example, the processor can estimate the type (e.g., vehicle type) of the external vehicle based on the length of the point cloud.

[0099] In one embodiment, the processor may identify a length 373 of the point cloud associated with the external vehicle 371. For example, the processor may identify the length 373 of the point cloud associated with the external vehicle 371 in an x-axis direction.

[0100] In one embodiment, the processor may determine that the length 373 of the point cloud associated with the external vehicle 371 is within the first range. The processor may remove first points identified at a first specific elevation or higher from a point cloud associated with the external vehicle 371 based on the length 373 of the point cloud associated with the external vehicle 371 being within the first range.

[0101] In one embodiment, the processor may generate a bounding box based on the point cloud from which the first points were removed.

[0102] For example, the presence of the length 373 of the point cloud in the first area may indicate that the type of the external vehicle 371 is of the first type, which includes a passenger vehicle.

[0103] In one embodiment, the processor may identify a length 363 of the point cloud associated with the external vehicle 361. For example, the processor may identify the length 363 of the point cloud associated with the external vehicle 361 in an x-axis direction.

[0104] In one embodiment, the processor may determine that the length 363 of the point cloud associated with the external vehicle 361 lies in a second range that is greater than the first range. The processor may remove second points identified at a second determined elevation or higher, which is higher than the first determined elevation, from the point cloud associated with the external vehicle 361 based on the length 363 of the point cloud associated with the external vehicle 361 being in the second range that is greater than the first range.

[0105] In one embodiment, the processor may generate a bounding box based on the point cloud from which the second points were removed.

[0106] For example, the presence of the point cloud length 363 in the second region may indicate that the type of external vehicle 361 is a second type, including at least one of a truck, a bus, or any combination thereof.

[0107] As mentioned above, according to one embodiment, the processor of the vehicle control device may remove points at a certain height or higher based on the length of the point cloud corresponding to the external vehicle (e.g., external vehicle 361 and / or external vehicle 371). The processor may remove points corresponding to the side view mirror of the external vehicle by removing points at a different certain height depending on the size of the external vehicle.

[0108] Fig. 4 shows an example of a vehicle control device that removes points with a certain height or higher in an embodiment of the present disclosure.

[0109] With reference to Fig. 4, a processor (e.g., processor 110 in Fig. 1) a vehicle control device (e.g., the vehicle control device 100 in Fig. 1) According to one embodiment, obtain a point cloud corresponding to an external vehicle. For example, the processor may obtain the point cloud corresponding to the external vehicle traveling on a different road than the road on which the vehicle (e.g., the host vehicle or subject vehicle) is traveling.

[0110] In one embodiment, the processor may identify a particular height 411 of a z-axis direction among an x-axis, a y-axis, and the z-axis.

[0111] For example, the processor may remove points 421 identified at the particular elevation 411 or higher based on obtaining the point cloud associated with the external vehicle. In the example of Fig. 4, the points 421 belonging to a side mirror are shown, but an embodiment is not limited thereto.

[0112] For example, the processor may remove only the points 421 corresponding to a side mirror of the external vehicle from the point cloud corresponding to the external vehicle, or remove all points identified at the specific height 411 or higher.

[0113] An example of Fig. 4 shows a point cloud expressed on a plane formed by the y-axis and the z-axis, but an embodiment is not limited thereto. For example, the processor may remove the points 421 identified at the specific height 411 or higher from the point cloud expressed on a plane formed by the x-axis and the z-axis. For example, the processor may remove the points 421 identified at the specific height 411 or higher from the point cloud expressed in a space formed by the x-axis, the y-axis, and the z-axis.

[0114] In one embodiment, the processor may generate a bounding box based on the point cloud from which the points 421 identified at the determined elevation 411 or higher have been removed.

[0115] As described above, according to one embodiment, the processor of the vehicle control device can generate a bounding box corresponding to the external vehicle by using the point cloud from which the points 421 have been removed based on removing the points 421 identified at the specific height 411 or higher. The processor can precisely identify a position of the bounding box corresponding to the external vehicle and / or a traveling direction of the bounding box by generating the bounding box based on the point cloud from which the points 421 identified at the specific height 411 or higher have been removed.

[0116] Fig. 5 shows an example of identifying a line segment of a bounding box corresponding to a side surface of the external vehicle based on an arrangement of contour points in an embodiment of the present disclosure.

[0117] With reference to Fig. 5, a processor (e.g., processor 110 in Fig. 1), which is used in a vehicle control device (e.g. the vehicle control device 100 in Fig. 1) according to one embodiment, identify a position of an external vehicle based on (e.g., relative to) a vehicle (e.g., the host vehicle or subject vehicle) 511.

[0118] For example, the left front of vehicle 511 may comprise quadrant I of a two-dimensional (2D) virtual coordinate system formed relative to vehicle 511. For example, the right front of vehicle 511 may comprise quadrant IV of a 2D virtual coordinate system formed relative to vehicle 511.

[0119] For example, the processor may identify an array of contour points corresponding to an outer perimeter (e.g., an outer contour, an outline) of an external vehicle 521 on the left front side of the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the external vehicle 521 based on identifying the array of contour points corresponding to the outer perimeter of the external vehicle 521 as being in a first shape.

[0120] For example, the processor may identify an array of contour points associated with an outer perimeter of an external vehicle 523 on the left front side of the vehicle 511. For example, the processor may identify a line segment associated with the side surface of the external vehicle 523 based on identifying the array of contour points associated with the outer perimeter of the external vehicle 523 as being in a second shape.

[0121] For example, the processor may identify the arrangement of contour points corresponding to an outer perimeter of an external vehicle 531 on the same road (e.g., in the same lane) as the vehicle 531. For example, the processor may identify a line segment corresponding to the side surface of the external vehicle 531 based on identifying the arrangement of contour points corresponding to the outer perimeter of the external vehicle 531 as being in a third shape.

[0122] For example, the processor may identify the arrangement of contour points corresponding to the outer perimeter of an external vehicle 533 on the same road (e.g., in the same lane) as the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the external vehicle 533 based on identifying the arrangement of contour points corresponding to the outer perimeter of the external vehicle 533 as being in a second shape.

[0123] For example, the processor may identify the arrangement of contour points corresponding to the outer perimeter of an external vehicle 541 on the right front side of the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the side surface of the external vehicle 541 based on identifying the arrangement of contour points corresponding to the outer perimeter of the external vehicle 541 as being in a fourth shape.

[0124] For example, the processor may identify the arrangement of contour points corresponding to the outer perimeter of an external vehicle 543 on the right front side of the vehicle 511. For example, the processor may identify a line segment corresponding to the side surface of the side surface of the external vehicle 543 based on identifying the arrangement of contour points corresponding to the outer perimeter of the external vehicle 543 as being in a third shape.

[0125] In one embodiment, the processor may identify representative points that represent a side surface of an external vehicle (e.g., external vehicle 521, external vehicle 523, external vehicle 531, external vehicle 533, external vehicle 541, and / or external vehicle 543).

[0126] Identifying the representative points that represent the side surface of the external vehicle will be discussed later in Fig. 6 described.

[0127] Fig. 6 shows an example of identifying representative points representing a side surface of an external vehicle in an embodiment of the present disclosure.

[0128] With reference to Fig. 6, a processor (e.g., processor 110 in Fig. 1), which is used in a vehicle control device (e.g. the vehicle control device 100 in Fig. 1) according to one embodiment, identify contour points representing an outer perimeter of an external vehicle from a point cloud.

[0129] Referring to a first example 601, in one embodiment, the processor may determine a peak point (e.g., t 3 or t 5) which is furthest from a line segment having a first endpoint (e.g. t 1 ) and a second endpoint (e.g. t 11 ) is removed. The processor may identify points 611 located within the line segment connecting the second endpoint and the peak point. The points 611 may, for example, be referred to as representative points representing a side surface of an external vehicle. The points 611 located within the line segment connecting the second endpoint and the peak point may include points identified in an area that is (e.g., at least partially) different from an area between a line segment associated with a side surface of a bounding box and / or a virtual box formed by the point cloud and the line segment connecting the second endpoint and the peak point.

[0130] Referring to a second example 603, in one embodiment, the processor may identify a plane having the longest reference line segment, indicating that the reference line segment indicating straightness is the longest, from a plurality of planes formed in the z-axis direction. For example, the reference line segment may be identified based on performing a convex hull algorithm.

[0131] In one embodiment, the processor may identify points spaced from the longest reference line segment within a reference distance (e.g., about 0.25 m). The processor may determine the points spaced from the longest reference line segment within the reference distance as representative points representing the side surface of the external vehicle.

[0132] Based on performing the operations described above, the processor may obtain representative points 613 of the second example 603.

[0133] Fig. 7 shows an example of determining whether to generate a final bounding box based on a lateral position of a bounding box in one embodiment of the present disclosure.

[0134] With reference to Fig. 7, a processor (e.g., processor 110 in Fig. 1) a vehicle control device (e.g., the vehicle control device 100 in Fig. 1) According to one embodiment, obtain a mean lateral axis value of representative points. For example, the mean lateral axis value of representative points may comprise an average of the y-coordinates of representative points.

[0135] In one embodiment, the processor may identify a distance 715 between the mean lateral axis value of the representative points and a line segment of a bounding box 711 corresponding to a side surface of an external vehicle. For example, the distance 713 and / or 715 between the mean lateral axis value of the representative points and the line segment of the bounding box 711 corresponding to the side surface of an external vehicle may be referred to as a "lateral position correction value."

[0136] In one embodiment, if the lateral position correction value is identified as being between 0 and a reference value, the processor may use bounding box 711 as the final bounding box. For example, the reference value may be half the width of bounding box 711.

[0137] In one embodiment, if the lateral position correction value is not identified between 0 and the reference value, the processor may obtain the final bounding box by additionally correcting the bounding box 711.

[0138] Fig. 8 shows an example of identifying a direction of travel based on representative points in an embodiment of the present disclosure.

[0139] With reference to Fig. 8, a processor (e.g., processor 110 in Fig. 1) a vehicle control device (e.g., the vehicle control device 100 in Fig. 1) According to one embodiment, obtain a bounding box 811 belonging to (e.g., corresponding to) an external vehicle. The processor may select an intermediate area 821 among representative points belonging to a side surface of the external vehicle as a high-reliability section.

[0140] The intermediate area 821 may, for example, comprise an area within a certain distance from a representative intermediate point 823 among the representative points. The certain (e.g., predetermined or specific) distance may be determined, for example, depending on the length of the external vehicle.

[0141] In one embodiment, the processor may identify a first representative point 825 that is closest to a front surface (e.g., a front surface) of the external vehicle among the representative points included in the intermediate region 821. The processor may identify a second representative point 827 that is closest to a rear surface (e.g., a rear surface) of the external vehicle among the representative points included in the intermediate region 821.

[0142] The processor may identify a half-line from the second representative point 827 to the first representative point 825. The processor may obtain a corrective travel direction 831 of the bounding box 811 based on the half-line from the second representative point 827 to the first representative point 825.

[0143] In one embodiment, the processor may determine an angular difference between the corrected travel direction 831 of the bounding box 811 and the travel direction of the bounding box 811. The processor may correct the bounding box 811 based on the angular difference between the corrected travel direction 831 of the bounding box 811 and the travel direction of the bounding box 811 exceeding a threshold angle. For example, the processor may obtain a final bounding box obtained by correcting the bounding box 811.

[0144] In one embodiment, the processor may use the bounding box 811 as the final bounding box based on (e.g., if) the angular difference between the correction travel direction 831 of the bounding box 811 and the travel direction of the bounding box 811 being less than or equal to the threshold angle.

[0145] Fig. 9 shows an example of using a virtual box and a bounding box in one embodiment of the present disclosure.

[0146] With reference to Fig. 9, a processor (e.g., processor 110 in Fig. 1) a vehicle control device (e.g., the vehicle control device 100 in Fig. 1) According to one embodiment, generate a virtual box 911 based on a point cloud associated with an external vehicle. The processor may generate a bounding box 913 based on removing at least a portion of the point cloud. For example, the bounding box 913 may include a final bounding box.

[0147] In one embodiment, the processor may assign a first identifier to the virtual box 911 generated from the point cloud.

[0148] In one embodiment, the processor may assign a second identifier to the bounding box 913 indicating that the bounding box 913 is generated based on the virtual box 911 to which the first identifier is assigned.

[0149] In one embodiment, the processor may identify the type of external vehicle based on the virtual box 911 to which the first identifier is assigned. For example, the processor may identify the type of external vehicle based on the size of the virtual box 911 to which the first identifier is assigned.

[0150] In one embodiment, the processor may track a travel route of the external vehicle based on the bounding box 913 assigned the second identifier. For example, the processor may identify a center point of the rear surface of the bounding box 913 assigned the second identifier, which corresponds to the center of the rear surface of the external vehicle, based on the bounding box 913 assigned the second identifier. The processor may track (e.g., monitor) the external vehicle based on a position of the center point of the rear surface.

[0151] As described above, according to one embodiment, the processor of the vehicle control device can accurately identify the type of the external vehicle by using the virtual box 911 generated by using all the points included in the point cloud. Furthermore, the processor can track the external vehicle by using the bounding box 913 generated by using a portion of the point cloud from which points of a portion corresponding to the side mirror have been removed, thereby accurately identifying the position of the external vehicle and / or the traveling direction of the external vehicle.

[0152] Fig. 10 shows an example of a flowchart related to a vehicle control method according to an embodiment of the present disclosure.

[0153] In the following, it can be assumed that the vehicle control device 100 of Fig. 1 for example, the process of Fig. 10. In addition, a description of Fig. 10, a process described as being performed by a processor, for example, may be controlled by the processor 110 of the vehicle control device 100.

[0154] At least one of the events of Fig. 10 can be controlled by the vehicle control device 100 from Fig. 1. Each of the operations in Fig. 10 can be executed sequentially, but does not necessarily have to be executed sequentially. For example, the order of operations can be changed, and at least two operations can be executed in parallel.

[0155] With reference to Fig. 10, a vehicle control method according to an embodiment may, in operation S1001, perform an operation of acquiring a plurality of points by removing points having a specific (e.g., predetermined or specific) height or higher (i.e., a specific height or a height higher than the specific height) from a point cloud based on acquiring the point cloud belonging to an external vehicle by a LiDAR (e.g., the LiDAR 120 in Fig. 1).

[0156] The vehicle control method according to an embodiment may include a process of removing the points having the specified height or higher from the point cloud belonging to the external vehicle based on a distance between a vehicle and the external vehicle being less than or equal to a second reference distance different from the first reference distance described later.

[0157] The vehicle control method according to an embodiment may include a process of identifying a length of the point cloud in a direction of a first axis among the first axis, a second axis, and a third axis, and removing first points identified at the first specified height or higher in the direction of the third axis based on the length of the point cloud being within a first range.

[0158] The vehicle control method according to an embodiment may include a process of removing second points identified at the second specific height or higher in a third axis direction based on the length of the point cloud being within a second range larger than the first range.

[0159] In operation S1003, the vehicle control method according to an embodiment may include an operation of generating a bounding box based on contour points indicating the outer periphery of the external vehicle among the plurality of points.

[0160] The vehicle control method according to an embodiment may include a process of identifying the contour points on each of a plurality of planes formed in a third axis direction among a first axis, a second axis, and the third axis, and generating the bounding box including the contour points identified on each of the plurality of planes.

[0161] In operation S1005, the vehicle control method according to an embodiment may include an operation of obtaining a final bounding box obtained by correcting the bounding box based on the angle between the first traveling direction of the virtual box through the point cloud and the second traveling direction of the bounding box exceeding the reference angle and the distance between the first position of the virtual box corresponding to the center of the rear surface of the external vehicle (e.g., corresponding to said center) and the second position of the bounding box corresponding to the center of the rear surface of the external vehicle (e.g., corresponding to said center) being less than or equal to the first reference distance.

[0162] The vehicle control method according to an embodiment may include a process of identifying an arrangement of the contour points based on a position at which the point cloud is identified, and identifying a first line segment of the bounding box belonging to a side surface of the external vehicle based on the position at which the point cloud is identified and the arrangement of the contour points.

[0163] The vehicle control method according to an embodiment may include a process of identifying a first end point and a second end point that are not connected to other contour points from the contour points, identifying a peak point that is farthest from a line segment connecting the first end point and the second end point, identifying a second line segment connecting the peak point and an end point belonging to the side surface of the external vehicle among the first end point and the second end point, and identifying representative points belonging to the side surface of the external vehicle in a range that is different from a range between the first line segment and the second line segment (e.g., at least partially).

[0164] According to one embodiment, the vehicle control method may further comprise obtaining a lateral position correction value of the bounding box based on a distance between the first line segment and an average of coordinate values ​​of the representative points in a second axis direction among a first axis, the second axis, and a third axis, and obtaining the final bounding box obtained by correcting the bounding box based on a difference between the lateral position correction value and a reference value being smaller than a threshold.

[0165] The vehicle control method according to an embodiment may include a process of identifying a representative intermediate point among the representative points, identifying a first representative point and a second representative point that are within a certain distance from the representative intermediate point and that are located farthest from the representative intermediate point in distance among the representative points, identifying the second traveling direction based on the first representative point and the second representative point, and obtaining the final bounding box based on a difference between the first traveling direction and the second traveling direction exceeding the reference angle.

[0166] The vehicle control method according to an embodiment may include a process of assigning a first identifier to the virtual box through the point cloud and assigning a second identifier to the final bounding box, which indicates that the final bounding box is generated by the virtual box to which the first identifier is assigned.

[0167] The vehicle control method according to an embodiment may include a process of identifying a type of the external vehicle based on the virtual box to which the first identifier is assigned and tracking a travel route of the external vehicle based on the final bounding box to which the second identifier is assigned.

[0168] As described above, the vehicle control method according to an embodiment can assist in operating the vehicle having the vehicle control device based on the final bounding box and the virtual box obtained from the point cloud belonging to the external vehicle.

[0169] Fig. 11 shows an example of a result of applying an embodiment of the present disclosure.

[0170] With reference to Fig. 11, a virtual box 1111 may include, in a first example 1101, an example in which points corresponding to a side mirror of an external vehicle are output without being removed.

[0171] A bounding box 1113 in a second example 1103 may include an example in which points corresponding to the side mirror of an external vehicle are output, the points being removed.

[0172] As shown in the second example 1103, the traveling direction of the external vehicle can be identified relatively precisely by outputting the bounding box 1113 based on the distance of the points belonging to the side mirror.

[0173] A vehicle control device and / or a vehicle control method according to an embodiment of the present disclosure can identify the traveling direction of the external vehicle relatively precisely, thereby supporting stable operation of a vehicle having the vehicle control device and / or the vehicle to which the vehicle control method is applied.

[0174] Fig. 12 illustrates a data processing system associated with a vehicle control apparatus or vehicle control method according to an embodiment of the present disclosure.

[0175] Referring to Fig. 12, a data processing system (e.g., a computing system, a computer system, or the like) 1000 may include at least a processor 1100, a memory 1300, a user interface input device 1400, a user interface output device 1500, a (data) storage device (e.g., a mass storage device) 1600, and a network interface 1700, which are interconnected via a bus 1200, and any combination thereof or all thereof may be present in plural or multiple components thereof may be present.

[0176] Processor 1100 may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in memory 1300 and / or storage device 1600. Memory 1300 and storage device 1600 may, for example, include various types of volatile or non-volatile storage media. For example, memory 1300 may include read-only memory (ROM) 1310 and random access memory (RAM) 1320.

[0177] Accordingly, operations of the method or algorithm described herein with respect to embodiments of the present invention may be implemented directly by hardware, a software module executed by the processor 1100, or a combination thereof. The software module may be located on a storage medium (i.e., the memory 1300 and / or the storage device 1600), such as a RAM, a flash memory, a ROM, an EPROM, an EEPROM, a register, a hard disk, a solid state disk (SSD), a removable disk, and a CD-ROM. The exemplary storage medium is coupled to the processor 1100, which may read information from and write information to the storage medium. Alternatively, the storage medium may be integrated with the processor 1100. The processor 1100 and the storage medium may be located in an application-specific integrated circuit (ASIC).The ASIC may be provided in a user terminal. Alternatively, the processor 1100 and the storage medium may be present as separate components in the user terminal.

[0178] Although the present disclosure has been described with reference to some exemplary embodiments and the accompanying drawings, the present disclosure is not necessarily limited thereto, but can be modified and altered in numerous ways by those skilled in the art to which the present disclosure pertains without departing from the spirit and scope of the present disclosure as defined by the following claims.

[0179] Therefore, the exemplary embodiments of the present disclosure are provided to explain the spirit and scope of the present disclosure, not to limit it, so that the spirit and scope of the present disclosure are not limited by the exemplary embodiments. The scope of the present disclosure may be interpreted based on the accompanying claims, and technical ideas within the range of equivalence to the claims may be included in the scope of the present disclosure.

[0180] Some embodiments may generate a bounding box obtained by excluding a portion corresponding to a side mirror of an external vehicle.

[0181] In addition, some embodiments may precisely identify a traveling direction of the external vehicle by generating the bounding box obtained by excluding a portion belonging to a side mirror of an external vehicle.

[0182] Furthermore, some embodiments may precisely identify the type of the external vehicle by identifying the type of the external vehicle using information including the side mirror, even when the bounding box excluding a portion belonging to a side mirror of an external vehicle is obtained.

[0183] A number of advantages can be derived directly or indirectly from the present disclosure.

Claims

[1] Vehicle control device (100) for a first vehicle, comprising: a LiDAR (120), a processor (110), and a memory connected to the processor (110) and storing instructions which, when executed by the processor (110), cause the processor (110) to: to obtain a plurality of points by removing a first set of points with a selected height or higher from a point cloud, based on the acquisition of the point cloud belonging to an external vehicle from the LiDAR (120), generate a bounding box (221) based on contour points of the plurality of points indicating an outer perimeter of the external vehicle, and to obtain a final bounding box obtained by correcting the bounding box (221) based on an angle (231) between a first travel direction (213) of a virtual box (211) through the point cloud and a second travel direction (223) of the bounding box (221) exceeding a reference angle, and based on a travel distance between a first position of the virtual box (211) corresponding to a center of a rear surface of the external vehicle and a second position of the bounding box corresponding to the center of the rear surface of the external vehicle being less than or equal to a first reference distance. [2] The vehicle control device (100) of claim 1, wherein the instructions further cause the processor (110) to remove the first set of points from the point cloud based on a vehicle distance (333, 337) between the first vehicle (331) and the external vehicle (341, 343) being less than or equal to a second reference distance (335). [3] The vehicle control device (100) of claim 1 or 2, wherein the selected height comprises a first selected height and a second selected height that exceeds the first selected height, and wherein the instructions further cause the processor (110) to: to identify a length (373, 363) of the point cloud in a direction of a first axis under the first axis, a second axis and a third axis, removing a first subset of the points identified at the first selected height or higher in a direction of the third axis based on the length (373) of the point cloud being within a first range, and removing a second subset of the points identified at the second selected elevation or higher in a direction of the third axis based on the length (363) of the point cloud being within a second range that is greater than the first range. [4] The vehicle control device (100) of any one of claims 1 to 3, wherein the instructions further cause the processor (110) to: to identify the contour points on each of a plurality of planes formed in a direction of a third axis among a first axis, a second axis and the third axis, and to create the bounding box containing the contour points identified on each of the planes. [5] The vehicle control device (100) of any one of claims 1 to 4, wherein the instructions further cause the processor (110) to: to identify an arrangement of the contour points based on a position at which the point cloud is identified, and to identify a first line segment of the bounding box, which belongs to a side surface of the external vehicle (521, 523, 531, 533, 541, 543), based on the position and arrangement of the contour points. [6] The vehicle control device (100) of claim 5, wherein the instructions further cause the processor (110) to: to identify a first endpoint and a second endpoint among the contour points, each of the first endpoint and the second endpoint being unconnected to any other of the contour points, to identify a vertex point which is furthest from a line segment connecting the first endpoint and the second endpoint, to identify a second line segment connecting the peak point and the first end point or the second end point, wherein the second line segment is included in a contour subset of the contour points belonging to a side surface of the external vehicle, and to identify representative points (611) belonging to the side surface of the external vehicle in a first area different from a second area between the first line segment and the second line segment. [7] The vehicle control device (100) of claim 6, wherein the instructions further cause the processor (110) to: to obtain a lateral position correction value (713) of the bounding box (711) based on a correction distance (715) between the first line segment and an average of coordinate values ​​of the representative points in a direction of a second axis among a first axis, the second axis and a third axis, and to obtain the final bounding box based on a difference between the lateral position correction value and a reference value being less than a threshold. [8] The vehicle control device (100) of claim 6 or 7, wherein the instructions further cause the processor (110) to: to identify a representative intermediate point (823) among the representative points, to identify a first representative point (825) and a second representative point (827) which are within a selected distance from the representative intermediate point (823) and which are spaced furthest from the representative intermediate point (823) among the representative points, to identify the second direction of travel based on the first representative point (825) and the second representative point (827), and to obtain the final bounding box based on a difference between the first direction of travel and the second direction of travel exceeding the reference angle. [9] The vehicle control device (100) of any one of claims 1 to 8, wherein the instructions further cause the processor (110) to: assigning a first identifier to the virtual box (911), and to assign a second identifier to the final bounding box (913) which indicates that the final bounding box (913) is generated by the virtual box (911) to which the first identifier is assigned. [10] The vehicle control device (100) of claim 9, wherein the instructions further cause the processor (110) to: to identify a type of external vehicle based on the virtual box (911) to which the first identifier is assigned, and to track a route of the external vehicle based on the final bounding box (913) to which the second identifier is assigned. [11] Vehicle control method, comprising: Obtaining a plurality of points by removing a first set of points having a selected height or higher from a point cloud of points based on obtaining the point cloud belonging to an external vehicle from a LiDAR (120) of a first vehicle, Creating a bounding box (221) based on contour points of the plurality of points indicating an outer perimeter of the external vehicle, and Obtaining a final bounding box, which is obtained by correcting the bounding box based on an angle (231) between a first direction of travel (213) of a virtual box (211) through the point cloud and a second direction of travel (223) of the bounding box (221) exceeding a reference angle, and based on a distance between a first position of the virtual box (211) corresponding to a center of a rear surface of the external vehicle and a second position of the bounding box (221) corresponding to the center of the rear surface of the external vehicle being less than or equal to a first reference distance. [12] The method of claim 11, further comprising: removing the first set of points from the point cloud based on a vehicle distance (333, 337) between the first vehicle (331) and the external vehicle (341, 343) being less than or equal to a second reference distance (335) [13] The method of claim 11 or 12, wherein the selected height comprises a first selected height and a second selected height that exceeds the first selected height, and wherein the method further comprises: Identifying a length (373, 363) of the point cloud in a direction of a first axis under the first axis, a second axis and a third axis, Removing a first subset of the points identified at the first determined height or higher in a direction of the third axis based on the length (737) of the point cloud being within a first range, and Removing a second subset of the points identified at the second determined height or higher in a direction of the third axis based on the length (363) of the point cloud being within a second range that is greater than the first range. [14] Method according to one of claims 11 to 13, further comprising: Identifying the contour points on each of a plurality of planes formed in a direction of a third axis among a first axis, a second axis and the third axis, and Creating the bounding box comprising the contour points identified on each of the plurality of planes. [15] Method according to one of claims 11 to 14, further comprising: Identifying an arrangement of the contour points based on a position at which the point cloud is identified, and Identifying a first line segment of the bounding box corresponding to a side surface of the external vehicle (521, 523, 531, 533, 541, 543) based on the position and arrangement of the contour points. [16] The method of claim 15, further comprising: Identifying a first endpoint and a second endpoint among the contour points, each of the first endpoint and the second endpoint being unconnected to any other of the contour points, Identifying a vertex point that is farthest from a line segment connecting the first endpoint and the second endpoint, Identifying a second line segment connecting the peak point to the first endpoint or the second endpoint, wherein the second line segment is included in a contour subset of the contour points belonging to the side surface of the external vehicle, and Identifying representative points (611) belonging to the side surface of the external vehicle in a first area different from a second area between the first line segment and the second line segment. [17] The method of claim 16, further comprising: Obtaining a lateral position correction value (713) of the bounding box (711) based on a correction distance (715) between the first line segment and an average of coordinate values ​​of the representative points in a direction of a second axis among a first axis, the second axis and a third axis, and Obtaining the final bounding box based on a difference between the lateral position correction value and a reference value being smaller than a threshold. [18] The method of claim 16 or 17, further comprising: Identifying a representative intermediate point (823) among the representative points, Identifying a first representative point (825) and a second representative point (827) which are within a selected distance from the representative intermediate point (823) and which are spaced furthest from the representative intermediate point (825) among the representative points, Identifying the second direction of travel based on the first representative point (825) and the second representative point (827), and Obtaining the final bounding box based on a difference between the first direction of travel and the second direction of travel exceeding the reference angle. [19] Method according to one of claims 11 to 18, further comprising: Assigning a first identifier to the virtual box (911), and Assigning, to the final bounding box (913), a second identifier indicating that the final bounding box (913) is generated by the virtual box (911) to which the first identifier is assigned. [20] The method of claim 19, further comprising: Identifying a type of external vehicle based on the virtual box (911) to which the first identifier is assigned, and Tracking a route of the external vehicle based on the final bounding box (913) to which the second identifier is assigned.

Images