Vehicle control apparatus and method thereof

Abstract

A vehicle control apparatus and a method thereof are provided. A vehicle control device includes light detection and ranging (LiDAR), a memory, and a processor. The processor generates a virtual meta object based on receiving information associated with the first plurality of points; identifying whether the converted virtual trajectory and the virtual metadata are associated with each other based on a point in time at which the virtual trajectory is converted to generate the virtual meta object; identifying whether a virtual meta object exists; determining whether a virtual trajectory is recognized in a first region formed at a distance spaced apart from the front of the vehicle by a first specified distance or more; and activating a function for determining whether to remove at least one virtual frame obtained from the second plurality of points using the virtual trajectory stored in the second space.

Description

Technical Field

[0001] The present disclosure relates to a vehicle control device and method thereof, and more particularly, to a technology using one or more sensors (eg, a light detection and ranging (LiDAR) sensor). Background Art

[0002] Accurate detection of external objects using various sensors may be helpful in assisting vehicle driving.

[0003] In particular, when the vehicle is operating in a driving assist device active mode or an autonomous driving mode, one or more sensors (eg, one or more LiDAR sensors) may be used to identify external objects.

[0004] Since light reflected from an external object is used to identify at least one of the position of the external object, the shape of the external object, the speed of the external object, or the type of the external object, or any combination thereof, when light reflected from the external object is incorrectly identified, the LiDAR sensor may generate a virtual frame corresponding to the external object in a space where there is no external object.

[0005] Incorrect detection and generation of virtual boxes may degrade the performance of the vehicle's object recognition and autonomous driving operations. Summary of the invention

[0006] The following summary provides a simplified summary of certain features. This summary is not an extensive overview and is not intended to identify key or critical elements.

[0007] An aspect of the present disclosure provides a vehicle control apparatus and method thereof for removing a virtual frame generated by noise.

[0008] Another aspect of the present disclosure provides a vehicle control apparatus and method thereof, the vehicle control apparatus being used to recognize noise generated by a road sign or a preceding vehicle and remove a virtual frame recognized as the noise.

[0009] Another aspect of the present disclosure provides a vehicle control device and a method thereof, the vehicle control device being used to remove a virtual frame recognized as noise to stably drive a vehicle control system associated with the vehicle control device.

[0010] The technical problems to be solved by the present disclosure are not limited to the above-mentioned problems, and those skilled in the art to which the present disclosure belongs will clearly understand any other technical problems not mentioned herein from the following description.

[0011] The vehicle control device may include: at least one sensor; a memory; and a processor, wherein the processor is configured to: generate a virtual meta-object based on receiving information associated with a first plurality of points of the object, wherein the first plurality of points are identified by a detection result of the at least one sensor and are located above a first reference height; determine whether a converted virtual trajectory is associated with the virtual meta-object, wherein the virtual trajectory stored in a first space of the memory is converted into a converted virtual trajectory corresponding to a time point at which the virtual meta-object is generated; determine whether the existence of the virtual meta-object is valid based on determining that the virtual meta-object and the converted virtual trajectory are not associated with each other; determine whether there is a virtual meta-object between the vehicle and the vehicle based on the virtual meta-object not being generated and the information not being received. The method comprises the steps of: determining whether a virtual track is recognized in a first area formed at a distance separated from the first area by a distance greater than the first distance; storing the virtual track recognized in the first area in a second space different from the first space of the memory; and determining whether to remove at least one virtual box obtained from a second plurality of points identified by a detection result of at least one sensor using the virtual track stored in the second space, wherein the virtual meta-object includes a closed boundary formed by the first plurality of points, wherein the first plurality of points corresponds to an object including a landmark, and wherein the virtual track includes a second closed boundary formed by a third plurality of points obtained at a time point different from a time point when the virtual meta-object is generated, and wherein the second closed boundary corresponds to the object.

[0012] The processor may be configured to determine whether the virtual meta-object and the converted virtual trajectory are associated with each other based on at least one of a distance between a first center point of the virtual meta-object and a second center point of the converted virtual trajectory, a ratio at which the virtual meta-object and the converted virtual trajectory overlap with each other, and any combination thereof.

[0013] The processor is configured to overwrite the virtual trajectory stored in the first space of the memory with the virtual meta-object based on determining that the virtual meta-object and the converted virtual trajectory are associated with each other.

[0014] The processor is configured to: determine that the virtual meta-object and the converted virtual trajectory are not associated with each other; and based on determining that the existence of the virtual meta-object is valid, generate a second virtual trajectory different from the converted virtual trajectory as the first virtual trajectory using the virtual meta-object.

[0015] The processor is configured to delete the virtual track stored in the memory based on determining that the vehicle is traveling on a road other than a straight road and including at least one of curvature, slope, and any combination thereof.

[0016] The processor is configured to delete the virtual track stored in the memory based on determining that at least one of the vertices forming the virtual track is identified in a second area formed at a distance less than the first distance from the vehicle.

[0017] The processor is configured to determine whether to remove at least one virtual frame obtained by a detection result of at least one sensor using the virtual trajectory based on determining that at least one vertex forming a vertex of the virtual trajectory is identified in a third area formed at a second distance from the vehicle, wherein the second distance is greater than the first distance.

[0018] The processor is configured to deactivate a function for determining whether to remove a virtual track identified by a detection result of the at least one sensor based on identifying all vertices forming the virtual track in a fourth area spaced apart from the vehicle by a distance greater than a second distance.

[0019] The processor is configured to determine whether to remove at least one virtual box based on at least one of determining whether the existence of the virtual meta-object is valid, a shape formed by a second plurality of points contained in the at least one virtual box, a width of the at least one virtual box, a length of the at least one virtual box, a height of a highest point of the at least one virtual box, and any combination thereof.

[0020] The processor is configured to: determine whether at least one virtual frame and the converted virtual track are associated with each other based on determining that the existence of the virtual meta-object is valid, the shape formed by the second plurality of points contained in the at least one virtual frame is a specified shape, the width of the at least one virtual frame is less than the first reference length, the length of the at least one virtual frame is less than the first reference length, and the height of the highest point of the at least one virtual frame from the ground is greater than the second reference length; and delete the at least one virtual frame based on determining that the at least one virtual frame and the converted virtual track are associated with each other.

[0021] A vehicle control method, comprising: generating a virtual meta-object based on receiving information associated with a first plurality of points of an object, wherein the first plurality of points are identified by detection results of at least one sensor and are located above a first reference height; determining whether a converted virtual trajectory is associated with the virtual meta-object, wherein the virtual trajectory stored in a first space of a memory is converted into a converted virtual trajectory corresponding to a time point at which the virtual meta-object is generated; determining whether the existence of the virtual meta-object is valid based on determining that the virtual meta-object and the converted virtual trajectory are not associated with each other; determining a first area formed at a distance spaced apart from the vehicle based on the virtual meta-object not being generated and the information not being received whether a virtual track is recognized in the first area, wherein the distance is greater than the first distance; storing the virtual track recognized in the first area in a second space different from the first space of the memory; and using the virtual track stored in the second space, determining whether to remove at least one virtual box obtained from a second plurality of points identified by the detection result of at least one sensor, wherein the virtual meta-object includes a closed boundary formed by the first plurality of points, wherein the first plurality of points corresponds to an object including a landmark, and wherein the virtual track includes a second closed boundary formed by a third plurality of points obtained at a time point different from the time point when the virtual meta-object is generated, and wherein the second closed boundary corresponds to the object.

[0022] These and other features and advantages are described in detail below. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other objects, features and advantages of the present disclosure will become more apparent through the following detailed description in conjunction with the accompanying drawings:

[0024] Figure 1 An example of a block diagram of a vehicle control device is shown;

[0025] Figure 2A An example is shown in which noise is generated by a preceding vehicle that is different from the vehicle;

[0026] Figure 2B An example of noise generated by light reflected from a road sign is shown;

[0027] Figure 3 An example of external objects and noise represented by LiDAR is shown;

[0028] Figure 4 An example of removing the virtual frame via vehicle controls is shown;

[0029] Figure 5A An example of a flow chart showing a vehicle control method;

[0030] Figure 5B An example of a flow chart showing a vehicle control method;

[0031] Figure 5C An example of a flow chart showing a vehicle control method;

[0032] Figure 6 An example of a flow chart illustrating a vehicle control method; and

[0033] Figure 7 An example of a computing system associated with a vehicle control device or a vehicle control method is shown. DETAILED DESCRIPTION

[0034] Various examples of the present disclosure will be described in detail below with reference to the exemplary drawings. In the drawings, the same reference numerals will be used to represent the same or equivalent components. In addition, in order to avoid unnecessarily obscuring the main points of the present disclosure, detailed descriptions of well-known features or functions will be excluded.

[0035] When describing the components of the exemplary embodiments of the present disclosure, the terms first, second, A, B, (a), (b), etc. may be used herein. These terms are only used to distinguish one component from another component, without limiting the corresponding components, regardless of the order or priority of the corresponding components. In addition, unless otherwise defined, all terms used herein, including technical and scientific terms, should be interpreted as the conventions of the field to which the present disclosure belongs. It should be understood that the terms used herein should be interpreted as having a meaning consistent with their meaning in the context of the present disclosure and the related art, and unless clearly defined herein, should not be interpreted in an idealized or overly formal sense.

[0036] The following will refer to Figures 1 to 7 Examples of the present disclosure are described in detail.

[0037] Figure 1 An example of a block diagram of a vehicle control device is shown.

[0038] refer to Figure 1 The vehicle control device 100 may be implemented inside or outside the vehicle, and some components included in the vehicle control device 100 may be implemented inside or outside the vehicle. In this case, the vehicle control device 100 may be configured integrally with the control unit in the vehicle, or may be implemented as a separate device connected to the control unit of the vehicle through one or more separate connectors and / or one or more communication interfaces. For example, the vehicle control device 100 may also include Figure 1 Parts not shown.

[0039] refer to Figure 1, the vehicle control device 100 may include a processor 110, one or more sensors (e.g., LiDAR 120), and a memory 130. The processor 110, one or more sensors (e.g., LiDAR 120), and the memory 130 may be electrically or operably coupled to each other through electronic components including a communication bus.

[0040] Hereinafter, the hardware parts being operably coupled to each other may include establishing a direct connection or an indirect connection between the hardware parts in a wired or wireless manner so that a second hardware among the hardware parts is controlled by the first hardware. Different blocks are shown, but the embodiment is not limited thereto. Figure 1 Some of the hardware parts of the vehicle control device 100 may be included in a single integrated circuit including a system on a chip (SoC). The types of hardware parts and / or the number of hardware parts included in the vehicle control device 100 are not limited to Figure 1 For example, the vehicle control device 100 may include only Figure 1 Some of the hardware parts shown.

[0041] The vehicle control device 100 may include hardware for processing data based on one or more instructions. For example, the hardware for processing data may include an arithmetic 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 dual-core, quad-core, hexa-core or octa-core, etc.

[0042] The LiDAR 120 included in the vehicle control device 100 may obtain a data set for identifying one or more objects in a surrounding space around the vehicle having the vehicle control device 100. For example, the LiDAR 120 may identify at least one of the position of one or more objects, the direction of movement of one or more objects, the speed of one or more objects, and any combination thereof based on a pulsed laser signal (or light) emitted from the LiDAR 120 being reflected from the one or more objects and returning to the LiDAR 120.

[0043] For example, the LiDAR 120 may obtain a data set including a plurality of points in a three-dimensional space (e.g., represented by an x-axis, a y-axis, and a z-axis) based on a pulsed laser signal reflected from one or more objects. For example, the LiDAR 120 may obtain a data set including a plurality of points in a space (e.g., represented by an x-axis, a y-axis, and a z-axis) based on receiving a pulsed laser signal in a specified period.

[0044] The processor 110 included in the vehicle control device 100 may emit light from the LiDAR 120 of the vehicle. For example, the LiDAR 120 may receive the light emitted from the vehicle, and the processor 110 may receive information associated with the received light and / or coordinates of one or more objects in a three-dimensional space. For example, the processor 110 may identify at least one of the position of one or more objects and the speed of one or more objects based on the time when the light emitted from the vehicle is transmitted and the time when the light emitted from the vehicle and reflected from the one or more objects is received.

[0045] For example, the processor 110 may obtain a data set including a plurality of points based on the time when the light emitted from the vehicle is transmitted and the time when the light emitted from the vehicle and reflected from one or more objects is received. The processor 110 may obtain a data set representing a plurality of points on a three-dimensional (3D) virtual coordinate system including an x-axis, a y-axis, and a z-axis. Each of the plurality of points may be represented by a coordinate in the 3D virtual coordinate system (e.g., a vector represented by (x, y, z)).

[0046] The memory 130 included in the vehicle control device 100 may include a hardware component for storing data and / or instructions input and / or output by the processor 110 of the vehicle control device 100 .

[0047] For example, the memory 130 may include a volatile memory (including a random access memory (RAM)) or a nonvolatile memory (including a read only memory (ROM)).

[0048] For example, the volatile memory may include at least one of a dynamic RAM (DRAM), a static RAM (SRAM), a cache RAM, a pseudo SRAM (PSRAM), and any combination thereof. For example, the non-volatile memory may include at least one of a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a flash memory, a hard disk, an optical disk, a solid state drive (SSD), an embedded multimedia card (eMMC), and any combination thereof.

[0049] The processor 110 of the vehicle control device 100 may receive information associated with a first plurality of points identified at a position above a first reference height (e.g., about 4 m) from the ground through the LiDAR 120. For example, the information associated with the first plurality of points identified at a position above the first reference height from the ground may be referred to as overhead box information.

[0050] The processor 110 may generate a virtual meta object based on receiving, through the LiDAR 120 , information associated with a first plurality of points identified at locations above a first reference height above the ground.

[0051] For example, the virtual meta-object may include a closed boundary (e.g., a rectangle) formed by a first plurality of points obtained based on information generated by detection of the LiDAR 120 and corresponding to an external object including a road sign. For example, the virtual meta-object may be represented as a rectangle formed by a first plurality of points obtained using the LiDAR 120 and corresponding to an external object including a road sign.

[0052] The processor 110 may convert the virtual track stored in the first space of the memory 130 into a converted virtual track corresponding to the time point at which the virtual meta-object is generated. The processor 110 may identify whether the converted virtual track and the virtual meta-object are associated with each other based on obtaining the converted virtual track. For example, the virtual track may include a rectangle formed by a third plurality of points obtained at different time points different from the time point at which the virtual meta-object is generated. For example, the different time points different from the time point at which the virtual meta-object is generated may include a time point before the time point at which the virtual meta-object is generated. For example, the virtual track may include a virtual box managed as an array in a designated space of the memory 130.

[0053] The processor 110 may identify a distance between a first center point of the virtual meta-object and a second center point of the converted virtual track. The processor 110 may identify a ratio at which the virtual meta-object and the converted virtual track overlap each other.

[0054] For example, the processor 110 may determine whether the virtual meta-object and the converted virtual trajectory are associated with each other based on at least one of a distance between a first center point of the virtual meta-object and a second center point of the converted virtual trajectory and / or a ratio at which the virtual meta-object and the converted virtual trajectory overlap with each other.

[0055] For example, the processor 110 may determine the correlation distance between the first center point and the second center point of the converted virtual trajectory based on the first center point of the virtual meta object and the second center point of the converted virtual trajectory. For example, the processor 110 may identify the Mahalanobis distance between the first center point and the second center point. The Mahalanobis distance may be determined as the distance of the test point from the centroid divided by the width of the ellipsoid in the direction of the test point. Based on the correlation distance (or Mahalanobis distance) between the first center point of the virtual meta object and the second center point of the converted virtual trajectory being less than the reference distance, the processor 110 may determine that the virtual meta object and the converted virtual trajectory are associated with each other. The processor 110 may determine that the virtual meta object and the converted virtual trajectory are not associated with each other based on the correlation distance (or Mahalanobis distance) between the first center point of the virtual meta object and the second center point of the converted virtual trajectory being greater than or equal to the reference distance.

[0056] For example, the processor 110 may identify a ratio at which the virtual meta-object and the converted virtual track overlap with each other. The processor 110 may determine that the virtual meta-object and the converted virtual track are associated with each other based on the ratio at which the virtual meta-object and the converted virtual track overlap with each other being greater than or equal to a reference ratio (e.g., approximately 25%).

[0057] For example, the processor 110 may determine that the virtual meta-object and the converted virtual track are not associated with each other based on the fact that the ratio at which the virtual meta-object and the converted virtual track overlap with each other is less than a reference ratio.

[0058] For example, the processor 110 may determine whether the virtual meta-object and the converted virtual trajectory are associated with each other based on a distance between a first center point of the virtual meta-object and a second center point of the converted virtual trajectory, and may determine whether the virtual meta-object and the converted virtual trajectory are associated with each other based on a ratio at which the virtual meta-object and the converted virtual trajectory overlap with each other (for example, when the virtual meta-object and the converted virtual trajectory are not associated with each other).

[0059] The processor 110 may determine that the virtual meta-object and the converted virtual trajectory are associated with each other. The processor 110 may rewrite the virtual trajectory stored in the first space of the memory 130 with the virtual meta-object based on determining that the virtual meta-object and the converted virtual trajectory are associated with each other.

[0060] For example, the processor 110 may overwrite the virtual trajectory stored in the first space of the memory 130 with the virtual meta object based on the virtual meta object and the converted virtual trajectory being associated with each other, thereby replacing the virtual trajectory stored in the first space with the virtual meta object.

[0061] The processor 110 may determine that the virtual meta-object and the converted virtual trajectory are not associated with each other. The processor 110 may determine whether the virtual meta-object exists based on identifying that the virtual meta-object and the converted virtual trajectory are not associated with each other. The processor 110 may use the virtual meta-object to generate a virtual trajectory different from the converted virtual trajectory. For example, the processor 110 may generate a second virtual trajectory different from the converted virtual trajectory as the first virtual trajectory. For example, the processor 110 may store the virtual trajectory in the memory 130 based on converting the virtual meta-object into the virtual trajectory.

[0062] The processor 110 may determine whether the virtual meta-object exists based on determining that the virtual meta-object is not associated with the converted virtual trajectory. For example, the processor 110 may not generate the virtual meta-object based on not receiving the first plurality of points identified at a position above a first reference height from the ground.

[0063] The processor 110 can determine whether a virtual track is identified in a first area formed at a distance from the front of the vehicle at a first specified distance (e.g., 15m) based on not generating a virtual meta-object depending on not receiving information associated with a first plurality of points identified at positions above a first reference height above the ground.

[0064] The processor 110 may store the virtual track recognized in the first area in a second space different from the first space of the memory 130. For example, the virtual track stored in the second space may be referred to as a virtual storage track.

[0065] When the vehicle is traveling on a straight road, the processor 110 may obtain at least one virtual frame from the second plurality of points identified using the LiDAR 120. When the vehicle is traveling on a straight road, the processor 110 may activate a function for determining whether to remove at least one virtual frame obtained from the second plurality of points identified by the detection result of the LiDAR 120 using the virtual track stored in the second space.

[0066] The processor 110 may determine that the vehicle is traveling on a road that is different from a straight road and includes at least one of curvature, slope, and any combination thereof. The processor 110 may delete the virtual track stored in the memory 130 based on determining that the vehicle is traveling on a road that is different from a straight road and includes at least one of curvature, slope, and any combination thereof. For example, a road that is different from a straight road and includes at least one of curvature, slope, and any combination thereof may be referred to as a ramp segment.

[0067] The processor 110 may delete the virtual track stored in the memory 130 based on determining that at least one of the vertices forming the virtual track is identified in the second area formed at a distance less than the first specified distance from the front of the vehicle. For example, the second area may be referred to as an air virtual track release range.

[0068] The processor 110 may activate a function for determining whether to use a virtual track to remove a virtual frame obtained from the detection result of the LiDAR 120 based on determining that at least one of the vertices forming the virtual track is identified in a third area formed at a distance greater than or equal to a first specified distance from the front of the vehicle and below a second specified distance (e.g., 80 m) greater than the first specified distance.

[0069] For example, the third area may be referred to as an erase area. For example, the third area may be referred to as a pseudo track removal logic operation range. The processor 110 may delete the pseudo track identified in the third area. For example, the pseudo track may include a virtual frame generated by noise. For example, the third area may be included in the first area.

[0070] The processor 110 may determine whether to remove the virtual frame based on at least one of whether a virtual meta-object exists, a shape formed by a second plurality of points contained in the virtual frame, a width of the virtual frame, a length of the virtual frame, a height of a highest point of the virtual frame, and any combination thereof.

[0071] For example, the processor 110 may determine that a virtual meta-object exists.

[0072] For example, the processor 110 may identify whether the shape formed by the second plurality of points included in the virtual frame is a specified shape. For example, the processor 110 may identify that the shape formed by the second plurality of points included in the virtual frame is a specified shape. For example, the specified shape may include an L-shape between an L-shape and an I-shape.

[0073] For example, the processor 110 may identify the width of the virtual frame. For example, the processor 110 may identify whether the width of the virtual frame is less than a first reference length (eg, approximately 1 m).

[0074] For example, the processor 110 may identify the length of the virtual frame. For example, the processor 110 may identify whether the length of the virtual frame is less than the first reference length.

[0075] For example, the processor 110 may identify the height of the highest point of the virtual frame. For example, the processor 110 may identify whether the height of the highest point of the virtual frame is greater than a second reference height (eg, approximately 2 m).

[0076] For example, the processor 110 may identify that a virtual meta-object exists, that a shape formed by a second plurality of points included in the virtual frame is a specified shape, that a width of the virtual frame is less than a first reference length, that a length of the virtual frame is less than the first reference length, and that a height of a highest point of the virtual frame from the ground is greater than a second reference length. The processor 110 may determine whether the virtual frame and the converted virtual track are associated with each other based on determining that a virtual meta-object exists, that a shape formed by a second plurality of points included in the virtual frame is a specified shape, that a width of the virtual frame is less than the first reference length, that a length of the virtual frame is less than the first reference length, and that a height of a highest point of the virtual frame from the ground is greater than a second reference length.

[0077] The processor 110 may delete the virtual frame based on determining that the virtual frame and the converted virtual track are associated with each other. For example, the deleted virtual frame may be referred to as a pseudo track. For example, the pseudo track may include a virtual frame identified by light reflected from a leading vehicle and a road sign. For example, the pseudo track may include a virtual frame identified by light reflected from a road sign.

[0078] The processor 110 may deactivate a function for determining whether to remove a virtual frame identified by the detection result of the LiDAR 120 based on determining that all vertices forming a virtual track are identified in a fourth area greater than a second specified distance from the front of the vehicle. For example, the fourth area may be included in the first area.

[0079] As described above, the processor 110 of the vehicle control device 100 can use at least one of a virtual track, a virtual meta-object, and any combination thereof to identify a pseudo track. The processor 110 can use at least one of a virtual track, a virtual meta-object, and any combination thereof to remove the pseudo track, thereby stabilizing the vehicle control system associated with the vehicle control device 100. For example, the driving path of the vehicle may be changed by the pseudo track, or the speed of the vehicle may be rapidly reduced by the pseudo track. However, the processor 110 of the vehicle control device 100 can use at least one of a virtual track, a virtual meta-object, and any combination thereof to remove the pseudo track, thereby preventing the driving path of the vehicle from being changed by the pseudo track, or preventing the speed of the vehicle from being rapidly reduced by the pseudo track.

[0080] Figure 2A An example is shown in which noise is generated by a preceding vehicle other than the vehicle.

[0081] Figure 2B An example of noise generated by light reflected from a road sign is shown.

[0082] Figure 1 The vehicle control device 100 can execute Figure 2A and / or Figure 2B For example, regarding the operation of vehicle controls Figure 2A and Figure 2BThe operation of the vehicle control device can be included in Figure 1 The processor 110 in the vehicle control device 100 executes.

[0083] Figure 2A and Figure 2B Examples of noise generated by objects (eg, road signs and / or leading vehicles) are shown.

[0084] Figure 2A and Figure 2B Examples of vehicles 200 and 250 and one or more objects of vehicles 200 and 250 may be included that are represented on a plane represented by an x-axis and a z-axis among the x-axis, the y-axis, and the z-axis. The x-axis may be parallel to the driving direction of the vehicle. The z-axis may be a vertical axis perpendicular to the x-axis.

[0085] refer to Figure 2A , the processor of the vehicle control device may control the LiDAR to emit light from the vehicle 200. The LiDAR may receive light reflected from the preceding vehicle 210 and the road sign 220.

[0086] Figure 2A An example state in which a pseudo track is generated by the light propagation path reflected at the preceding vehicle 210 and the road sign 220 is shown, which will be described below.

[0087] For example, Figure 2A The vehicle 200 may be equipped with a LiDAR at a height of about 0.6 m from the ground. Light emitted from the LiDAR mounted on the vehicle 200 may be reflected from the rear end of the preceding vehicle 210 and then reflected from the road sign 220. For example, the height 215 of the rear end of the preceding vehicle 210 may be about 1 m. For example, the height 240 of the road sign 220 may be about 5 m. In an example, the road sign 220 may be spaced apart from the vehicle 200 by a distance 235 (for example, it may be about 48 m).

[0088] The light emitted by the LiDAR mounted on the vehicle 200 is reflected from the rear end of the preceding vehicle 210 and then incident on the road sign 220. For example, it may be emitted at an angle of about 2.1 degrees relative to the ground.

[0089] The LiDAR may receive light traveling along path 225 that is reflected from vehicle 200 by preceding vehicle 210 and road signs 220 .

[0090] The processor may identify a plurality of points represented at an altitude of approximately 2.36 m based on receiving light reflected from vehicle 200 by preceding vehicle 210 and road signs 220 traveling along path 225 .

[0091] The processor may output a pseudo track 230 based on the angle of light emitted by the LiDAR, the distance 235 between the road sign 220 and the vehicle 200 (e.g., based on the travel time of the light along the path 225), and the installation height of the LiDAR. For example, the pseudo track 230 may be generated by multiple points of light reflected by the leading vehicle 210 and the road sign 220. Because the pseudo track 230 is often identified as a static object, it is necessary to remove the pseudo track 230 to enhance the accurate detection of one or more objects in the driving path.

[0092] refer to Figure 2B , the processor may emit light from the vehicle 250 along a path 280. Based on emitting light along the path 280, the LiDAR may receive light reflected from the road sign 260. The height 265 at which the road sign 260 is installed may be about 5 m.

[0093] The processor may identify the pseudo track 270 through the light reflected by the road sign 260. For example, the pseudo track 270 may include a virtual frame that does not correspond to an external object. For example, the height 285 at which the pseudo track 270 is identified may be about 3 m or less.

[0094] exist Figure 2A and Figure 2B In the present invention, the processor needs to remove the false tracks 230 and 270 to provide accurate object detection results. When the false tracks 230 and 270 are identified, it may cause an error in the vehicle control system associated with the vehicle control device. Hereinafter, a description of the vehicle control device for removing the false tracks 230 and 270 will be given below.

[0095] Figure 3 An example of external objects and noise represented by LiDAR is shown.

[0096] Figure 3 The operation of the device shown can be performed by Figure 1 The vehicle control device 100 executes. For example, Figure 3 The operation can be included in Figure 1 It is executed by the processor 110 in the vehicle control device 100.

[0097] Figure 3 The first example 301 may include an example associated with the vehicle's surrounding environment. Figure 3 A second example may include an example in which multiple points obtained by LiDAR are represented on a plane formed by the y-axis and the z-axis among the x-axis, the y-axis, and the z-axis (for example, the x-axis may be parallel to the direction of travel of the vehicle or in a direction from the rear center of the vehicle toward the front center of the vehicle, the y-axis may be a horizontal axis perpendicular to the x-axis, and the z-axis may be a vertical axis perpendicular to the x-axis and the y-axis). Figure 3A third example may include an example in which a plurality of points obtained by LiDAR are represented on a plane formed by an x-axis and a y-axis among the x-axis, the y-axis, and the z-axis.

[0098] refer to Figure 3 In the first example 301, the processor of the vehicle control device can identify the road sign 310. For example, the processor of the vehicle control device can identify a plurality of points and / or a virtual frame corresponding to the road sign 310 based on light emitted from the LiDAR being reflected by the road sign 310 and received by the LiDAR.

[0099] The processor may identify a plurality of points and / or virtual boxes through the crosstalk noise of the landmark 310 and the plurality of points and / or virtual boxes corresponding to the landmark 310. The virtual box caused by the crosstalk noise of the landmark 310 may be referred to as a pseudo track.

[0100] The second example 303 may include an example of a plurality of points 330 caused by the crosstalk noise of the road sign 310 of the first example 301. For example, the processor may obtain a virtual frame 350 based on the plurality of points 330.

[0101] In the third example 305, the virtual frame 350 may include a virtual frame corresponding to an external object and a virtual frame generated by noise. Since the virtual frame generated by noise in the virtual frame 350 is often recognized as a static object, the vehicle control device needs to remove the virtual frame generated by noise.

[0102] Figure 4 An example of removing the virtual frame via vehicle controls is shown.

[0103] about Figure 4 The operation of the device shown can be performed by Figure 1 For example, regarding Figure 4 The operations shown can be performed by including Figure 1 The processor 110 in the vehicle control device 100 executes.

[0104] refer to Figure 4 When the vehicle 400 is traveling, the processor of the vehicle control device may obtain a plurality of points and / or virtual frames based on the detection result of the light reflected from the external object by the LiDAR device. Hereinafter, the plurality of virtual frames and / or virtual frames may include a virtual track and / or a virtual meta-object.

[0105] For example, when the vehicle 400 is traveling, the processor may obtain a virtual frame 411 corresponding to the road sign 410 based on receiving light reflected from the road sign 410. For example, the processor may use the virtual frame 411 corresponding to the road sign 410 as a virtual meta-object and / or a virtual track. For example, the virtual meta-object may include a reference Figure 1For example, a virtual track may include a reference Figure 1 Describe the virtual trajectory.

[0106] The processor may recognize a position change of the vehicle 400 on a plane formed by the x-axis and the y-axis among the x-axis, the y-axis, and the z-axis. For example, the processor may recognize that the vehicle 400 is traveling in the positive direction 405 of the x-axis. When the vehicle 400 is traveling in the positive direction 405 of the x-axis, the processor may recognize that the virtual frames 411, 413, 415, and 417 corresponding to the road sign 410 move.

[0107] When the virtual frames 411, 413, 415, and 417 corresponding to the road sign 410 move, the processor can identify noise (e.g., a pseudo track) generated by the road sign 410. The processor can activate or deactivate a function for removing the noise generated by the road sign 410 depending on the positions where the virtual frames 411, 413, 415, and 417 are identified.

[0108] The processor may identify a first area formed at a distance spaced apart from the front of the vehicle 400 by more than a first designated distance (eg, approximately 15 m).

[0109] The processor may identify the second area 430 formed at a distance less than the first designated distance from the front of the vehicle 400. For example, when the virtual frame is identified in the second area 430, the processor may assign an identifier including "ActivateEraser=0".

[0110] The processor may identify a third area 440 formed at a distance greater than or equal to a first specified distance from the front of the vehicle 400 and below a second specified distance (e.g., about 80 m) greater than the first specified distance. For example, the first area may include the third area 440. For example, when a virtual frame is identified in the third area 440, the processor may assign an identifier including "ActivateEraser=1".

[0111] The processor may generate a virtual frame 411 corresponding to the road sign 410. The processor may store the virtual frame 411 corresponding to the road sign 410 in a memory. The processor may use the stored virtual frame 411 as data for tracking an external object (e.g., the road sign 410). The data for tracking an external object may be referred to as a virtual track. Hereinafter, the virtual frame tracked when the virtual frame 411 changes position as the vehicle 400 moves is referred to as a virtual track.

[0112] The processor may identify the virtual track 417 in the second area 430. The processor may identify at least a portion of the virtual track 417 in the second area 430. For example, the processor may remove the virtual track 417 based on identifying at least one of the vertices of the virtual track 417 in the second area 430. For example, the processor may remove the virtual track 417 stored in the memory based on identifying at least one of the vertices of the virtual track 417 in the second area 430.

[0113] The processor may identify the virtual track 415 at least partially included in the third area 440. The processor may activate a function for removing a pseudo track based on identifying the virtual track 415 at least partially included in the third area 440. For example, the pseudo track may be generated by light reflected from a preceding vehicle and / or a road sign.

[0114] If at least a portion of the virtual track 415 in the third area 440 is not identified, the processor may deactivate a function for removing the pseudo track.

[0115] The function of removing false traces will be described below.

[0116] The processor may identify the virtual track 420 in the third area 440. The processor may identify virtual frames 421 and 423 in the third area 440 based on the recognition of the virtual track 420 in the third area 440.

[0117] The processor may identify whether the virtual track 420 and the virtual frames 421 and 423 identified in the third area 440 are associated with each other. For example, the processor may identify whether the virtual track 420 and each of the virtual frames 421 and 423 overlap with each other at a ratio greater than a specified ratio (e.g., about 25%). For example, the processor may identify the correlation distance between the center point of the virtual track 420 and the center point of each of the virtual frames 421 and 423. The processor may identify that the correlation distance between the center point of the virtual track 420 and the center point of each of the virtual frames 421 and 423 is greater than a specified distance. For example, the correlation distance may include a Mahalanobis distance.

[0118] The processor may recognize that the virtual track 420 and each of the virtual frames 421 and 423 are associated with each other based on determining that the virtual track 420 and each of the virtual frames 421 and 423 overlap with each other at a ratio greater than a specified ratio. The processor may remove the virtual frames 421 and 423 based on the virtual track 420 and each of the virtual frames 421 and 423 being associated with each other. For example, the processor may remove the virtual frames 421 and 423, and may output the result of the removal.

[0119] The processor may recognize that the virtual track 420 and each of the virtual frames 421 and 423 are associated with each other based on determining that the correlation distance between the center point of the virtual track 420 and the center point of each of the virtual frames 421 and 423 is less than the specified distance. The processor may remove the virtual frames 421 and 423 based on the virtual track 420 and each of the virtual frames 421 and 423 being associated with each other. The processor may remove the virtual frames 421 and 423, and may output the result of the removal.

[0120] The processor may recognize that the virtual track 420 and each of the virtual frames 421 and 423 are not associated with each other based on determining that the virtual track 420 and each of the virtual frames 421 and 423 overlap with each other at a ratio less than a specified ratio. The processor may maintain the virtual frames 421 and 423 based on the virtual track 420 and each of the virtual frames 421 and 423 being not associated with each other. The processor may output a result of maintaining the virtual frames 421 and 423. The processor may output information associated with an external object corresponding to each of the virtual frames 421 and 423 together with each of the virtual frames 421 and 423 by outputting a result of maintaining the virtual frames 421 and 423.

[0121] The processor may recognize that the virtual track 420 and each of the virtual frames 421 and 423 are not associated with each other based on determining that the correlation distance between the center point of the virtual track 420 and the center point of each of the virtual frames 421 and 423 is greater than or equal to the specified distance. The processor may maintain the virtual frames 421 and 423 based on determining that the virtual track 420 and each of the virtual frames 421 and 423 are not associated with each other. The processor may output a result of maintaining the virtual frames 421 and 423. The processor may output information associated with an external object corresponding to each of the virtual frames 421 and 423 together with each of the virtual frames 421 and 423 by outputting a result of maintaining the virtual frames 421 and 423.

[0122] For example, the information associated with the external object corresponding to each of the virtual frames 421 and 423 may include at least one of the speed of the external object, the type of the external object, the state of the external object (e.g., static and / or moving state), and any combination thereof.

[0123] As described above, the processor may remove or maintain the virtual frames 421 and 423 based on the function for removing the virtual frames 421 and 423 (e.g., pseudo tracks) identified in the designated area (e.g., the third area 440). The processor may remove or maintain the virtual frames 421 and 423 based on executing the function for removing the virtual frames 421 and 423, thereby providing assistance in driving the vehicle 400 in the vehicle control system associated with the vehicle control device. For example, the processor may remove the pseudo track to provide assistance in maintaining the driving path of the vehicle 400 or maintaining the speed.

[0124] Figure 5A An example of a flow chart of a vehicle control method is shown.

[0125] Figure 5B An example of a flow chart of a vehicle control method is shown.

[0126] Figure 5C An example of a flow chart of a vehicle control method is shown.

[0127] FIG. 5A to FIG. 5C The operation of the device shown can be performed by Figure 1 For example, regarding FIG. 5A to FIG. 5C The operations shown can be performed by including Figure 1 The processor 110 in the vehicle control device 100 executes.

[0128] FIG. 5A to FIG. 5C At least one of the operations shown may be performed by Figure 1 The vehicle control device 100 performs the following steps. FIG. 5A to FIG. 5C The various operations shown may be performed sequentially, but not necessarily sequentially. For example, the order of the various operations may be changed, and at least two operations may be performed in parallel.

[0129] refer to Figure 5A In S501, the vehicle control method may include: generating a virtual meta-object based on information associated with a first plurality of points identified at positions above a first reference height from the ground.

[0130] For example, the virtual meta-object may include a rectangle formed by a first plurality of points obtained by LiDAR and corresponding to an external object including a road sign.

[0131] In S503, the vehicle control method may include: converting the virtual track stored in the first space of the memory to the current time point. For example, the virtual track may include a rectangle formed by a third plurality of points obtained at a time point different from the time point of generating the virtual meta-object.

[0132] In S505, the vehicle control method may include: identifying whether the virtual meta-object and the virtual track are associated with each other. For example, the vehicle control method may include: identifying whether the virtual meta-object and the virtual track are associated with each other based on at least one of the degree to which the virtual meta-object and the virtual track overlap with each other, the relative distance between the center point of the virtual track and the center point of the virtual meta-object, and any combination thereof.

[0133] When the virtual meta-object and the virtual track are associated with each other ("Yes" in S505), in S507, the vehicle control method may include: updating the virtual track based on the virtual meta-object and the virtual track being associated with each other. For example, the updating of the virtual track may include: replacing the virtual track stored in the first space of the memory with the virtual meta-object. For example, the updating of the virtual track may include: overwriting the virtual track stored in the first space of the memory with the virtual meta-object.

[0134] When the virtual meta-object and the virtual track are not associated with each other (No in S505), in S511, the vehicle control method may include: identifying whether the virtual meta-object exists. For example, the virtual meta-object may include a virtual frame corresponding to the external object recognized at the current time point.

[0135] If the virtual meta-object exists ("Yes" of S511), then in S509, the vehicle control method may include: generating a new virtual track. For example, generating the new virtual track may include: generating a virtual track corresponding to the virtual meta-object. For example, the vehicle control method may include: generating a virtual track corresponding to the virtual meta-object; and storing and managing the virtual track in a space different from the first space of the memory.

[0136] For example, generating a new virtual trajectory may include generating a virtual trajectory for tracking a new external object.

[0137] If there is no virtual meta-object (No in S511), then in S513, the vehicle control method may include: identifying whether there is a virtual track in the first area formed at a distance greater than a first specified distance (e.g., about 15 m) apart. For example, the vehicle control method may include: identifying whether there is a virtual track in the first area formed at a distance greater than a first specified distance apart from the vehicle.

[0138] If there is a virtual track in the first area formed at a distance greater than the first specified distance ("Yes"-S513), then in S515, the vehicle control method may include: deleting the virtual track. For example, the vehicle control method may include: deleting the virtual track stored in the first space of the memory.

[0139] If there is no virtual track in the first area formed at a distance greater than the first specified distance (No in S513), then in S517, the vehicle control method may include storing the virtual track in a second space different from the first space of the memory. For example, storing the virtual track in the second space different from the first space of the memory may include forming a virtual storage track and managing the virtual track.

[0140] refer to Figure 5B , in S519 , the vehicle control method may include: identifying whether the vehicle is traveling on a straight road.

[0141] For example, a road other than a straight road may be referred to as a slope section.

[0142] If the vehicle is traveling on a straight road ("Yes" in S519), then in S521, the vehicle control method may include: deleting the virtual track. For example, the vehicle control method may include: deleting the virtual track stored in the memory. For example, the vehicle control method may include: deleting the virtual stored track stored in the memory. For example, the vehicle control method may include: deleting all data sets associated with the virtual track stored in the memory.

[0143] If the vehicle is not traveling on a straight road (No in S519), then in S523, the vehicle control method may include: identifying whether at least one of the vertices forming the virtual track exists in the release area. For example, the release area may include an area formed within a first specified distance (e.g., about 15m) from the front of the vehicle.

[0144] If at least one of the vertices forming the virtual track exists in the release area (Yes in S523), then in S525, the vehicle control method may include deleting the virtual track. For example, the vehicle control method may include deleting the virtual track stored in the first space of the memory.

[0145] If at least one of the vertices forming the virtual trajectory does not exist in the release area (No in S523 ), the vehicle control method may identify whether at least one of the vertices forming the virtual trajectory exists in the operation area in S527 .

[0146] For example, the operation area may include an area formed at a distance greater than or equal to a first designated distance from the front of the vehicle and below a second designated distance greater than the first designated distance.

[0147] If at least one of the vertices forming the virtual track does not exist in the operation area (No of S527 ), in S529 , the vehicle control method may include deactivating a function for determining whether to remove a virtual frame obtained through a detection result of LiDAR.

[0148] If at least one of the vertices forming the virtual track exists in the operation area ("Yes" of S527), then in S531, the vehicle control method may include: activating a function for determining whether to remove the virtual frame obtained by the detection result of the LiDAR. For example, the function for determining whether to remove the virtual frame obtained by the detection result of the LiDAR may be referred to as a pseudo track removal function.

[0149] refer to Figure 5C In S533, the vehicle control method may include: identifying whether a virtual track exists. For example, the vehicle control method may include: identifying whether a virtual track exists in a memory. For example, the vehicle control method may include: identifying whether a virtual track exists in a designated space (e.g., the first space and / or the second space) in the memory.

[0150] If the virtual track exists (Yes in S533 ), then in S535 , the vehicle control method may include identifying whether the virtual frame obtained from the detection result of the LiDAR satisfies a specified condition.

[0151] For example, the specified condition may be associated with at least one of whether there is at least one virtual box, a shape formed by a second plurality of points contained in the at least one virtual box, a height of a highest point of the at least one virtual box, a width of the at least one virtual box, a length of the at least one virtual box, and any combination thereof.

[0152] For example, satisfying the specified condition may include a condition when there is at least one virtual frame, a condition when a shape formed by a second plurality of points included in at least one virtual frame is a specified shape, a condition when the height of the highest point of at least one virtual frame is greater than a reference height (e.g., approximately 2 m), a condition when the width of at least one virtual frame is less than a reference width (e.g., approximately 1 m), and a condition when the length of at least one virtual frame is less than a reference length (e.g., approximately 1 m). For example, the specified shape may include an L-shape between an L-shape and an I-shape. For example, the L-shape may include when the second plurality of points included in at least one virtual frame are arranged in an "L" shape.

[0153] For example, failure to satisfy the specified condition may include a condition when at least one virtual box does not exist, a condition when a shape formed by a second plurality of points contained in at least one virtual box is not a specified shape, a condition when a height of the highest point of at least one virtual box is less than or equal to a reference height, a condition when a width of at least one virtual box is greater than or equal to a reference width, or a condition when a length of at least one virtual box is greater than or equal to a reference length.

[0154] At least one virtual frame that satisfies all of the above specified conditions may be selected as a candidate for a false track. For example, the vehicle control method may include removing all or some of the virtual frames selected as candidates for the false track.

[0155] In S537 , the vehicle control method may include identifying whether the virtual frame and the virtual track satisfying the specified condition are associated with each other.

[0156] For example, the vehicle control method may include identifying whether the virtual frame and the virtual track are associated with each other based on at least one of a ratio at which the virtual frame and the virtual track overlap with each other, a distance between a center point of the virtual frame and a center point of the virtual track, and any combination thereof.

[0157] For example, the vehicle control method may include recognizing that the virtual frame and the virtual track are associated with each other based on determining that the virtual frame and the virtual track overlap with each other at a specified ratio (eg, approximately 25%) or more.

[0158] For example, the vehicle control method may include recognizing that the virtual frame and the virtual track are associated with each other based on determining that a correlation distance between a center point of the virtual frame and a center point of the virtual track is less than a reference length.

[0159] For example, the vehicle control method may include recognizing that the virtual frame and the virtual track are not associated with each other based on determining that the virtual frame and the virtual track overlap each other at a ratio less than a specified ratio.

[0160] For example, the vehicle control method may include recognizing that the virtual frame and the virtual track are not associated with each other based on determining that the correlation distance between the virtual frame and the virtual track is greater than or equal to the reference length.

[0161] For example, the vehicle control method may include identifying a relative distance between a center point of the virtual frame and a center point of the virtual track based on determining that the virtual frame and the virtual track overlap each other at a ratio less than a specified ratio.

[0162] If it is determined that the virtual trajectory and all or some of the virtual frames in the virtual frame selected as the pseudo trajectory candidates are associated with each other, then because all or some of the virtual frames in the virtual frame selected as the pseudo trajectory candidates associated with the virtual trajectory are pseudo trajectory, the vehicle control method (or vehicle control device) may include: deleting the pseudo virtual trajectory and all or some of the virtual frames in the virtual frame selected as the pseudo trajectory candidates.

[0163] The vehicle control method may select a candidate pseudo trajectory and remove the pseudo trajectory depending on whether the selected pseudo trajectory and the virtual trajectory are associated, thereby providing assistance for vehicle driving.

[0164] Figure 6 An example of a flow chart of a vehicle control method is shown.

[0165] Figure 6 The operation of the device shown can be performed by Figure 1 The vehicle control device 100 executes. For example, Figure 6 The operations shown can be performed by including Figure 1 The processor 110 in the vehicle control device 100 executes.

[0166] Figure 6 At least one of the operations shown may be performed by Figure 1 The vehicle control device 100 is executed. Figure 6 The various operations of can be performed sequentially, but not necessarily sequentially. For example, the order of the various operations can be changed, and at least two operations can be performed in parallel.

[0167] refer to Figure 6 In S601, the vehicle control method may include: generating a virtual meta-object based on information associated with a first plurality of points identified at positions above a first reference height from the ground received through LiDAR.

[0168] For example, the virtual meta-object may include a virtual frame formed by a first plurality of points obtained through the detection result of LiDAR and corresponding to an external object including a road sign.

[0169] In S603 , the vehicle control method may include: based on determining that the virtual trajectory stored in the first space of the memory is converted to a time point at which the virtual metadata is generated to obtain a converted virtual trajectory, identifying whether the converted virtual trajectory and the virtual metadata are associated with each other.

[0170] For example, the virtual track may include a rectangle formed by a third plurality of points obtained at a time point different from a time point at which the virtual meta-object is generated.

[0171] For example, the vehicle control method may include: identifying whether the virtual meta-object and the converted virtual track are associated with each other based on at least one of a distance between a first center point of the virtual meta-object and a second center point of the converted virtual track, a ratio at which the virtual meta-object and the converted virtual track overlap with each other, and any combination thereof.

[0172] The vehicle control method may include overwriting the virtual trajectory stored in the first space of the memory with the virtual meta object based on determining that the virtual meta object and the converted virtual trajectory are associated with each other.

[0173] In S605 , the vehicle control method may include: based on determining that the virtual meta-object and the virtual track are not associated with each other, identifying whether the virtual meta-object exists.

[0174] The vehicle control method may include: identifying whether the virtual meta-object and the converted virtual track are not associated. The vehicle control method may include: based on identifying that the virtual meta-object and the converted virtual track are not associated with each other and there is a virtual meta-object, generating a second virtual track different from the converted virtual track as the first virtual track using the virtual meta-object.

[0175] In S607, the vehicle control method may include: determining whether a virtual track is identified in a first area formed at a distance greater than a first specified distance from the front of the vehicle based on the fact that no virtual meta-object is generated due to the fact that information associated with a first plurality of points identified at a position above a first reference height from the ground is not received through a detection result of the LiDAR.

[0176] In S609 , the vehicle control method may store the virtual track identified at a distance greater than the first specified distance in a second space different from the first space of the memory.

[0177] The vehicle control method may include deleting a virtual track stored in a memory based on determining that the vehicle is traveling on a road other than a straight road and including at least one of curvature, slope, and any combination thereof.

[0178] In S611, the vehicle control method may include: based on determining that the vehicle is traveling on a straight road, activating a function for determining whether to remove at least one virtual frame obtained from the second plurality of points through the detection result of the LiDAR using the virtual track stored in the second space.

[0179] The vehicle control method may include deleting the virtual track stored in the memory based on determining that at least one of the vertices forming the virtual track is recognized in a second area formed less than a first specified distance from the front of the vehicle.

[0180] The vehicle control method may include: based on determining that at least one vertex among the vertices forming a virtual trajectory is identified in a third area formed at a distance greater than or equal to a first specified distance from the front of the vehicle and below a second specified distance greater than the first specified distance, activating a function for determining whether to remove a virtual frame obtained by LiDAR.

[0181] The vehicle control method may include: based on determining that all vertices forming the virtual track are identified in a fourth area greater than a second specified distance from the front of the vehicle, deactivating a function for determining whether to remove the virtual frame identified by the detection result of the LiDAR.

[0182] The vehicle control method may include: determining whether to remove the virtual frame based on at least one of whether a virtual meta-object exists, a shape formed by a second plurality of points contained in the virtual frame, a width of the virtual frame, a length of the virtual frame, a height of the highest point of the virtual frame, and any combination thereof.

[0183] For example, the vehicle control method may include: determining whether the virtual frame and the converted virtual track are associated with each other based on determining that a virtual element object exists, a shape formed by a second plurality of points contained in the virtual frame is a specified shape (e.g., an L-shape), a width of the virtual frame is less than a first reference length (e.g., approximately 1 m), a length of the virtual frame is less than the first reference length, and a height of the highest point of the virtual frame from the ground is greater than a second reference length (e.g., approximately 2 m).

[0184] For example, the vehicle control method may include deleting the virtual frame based on determining that the virtual frame and the converted virtual track are associated with each other.

[0185] According to one aspect of the present disclosure, a vehicle control device may include light detection and ranging (LiDAR), a memory, and a processor. The processor may generate a virtual meta-object based on receiving information associated with a first plurality of points identified at a position above a first reference height from the ground through LiDAR, may identify whether the converted virtual track and the virtual meta-object are associated with each other based on converting a virtual track stored in a first space of the memory to a time point at which the virtual meta-object is generated to obtain the converted virtual track, may identify whether the virtual meta-object exists based on the virtual meta-object and the converted virtual track are not associated with each other, may determine whether the virtual track is identified in a first area formed at a distance of more than a first specified distance from the front of the vehicle based on not generating the virtual meta-object due to not receiving the information, may store the virtual track identified in the first area in a second space different from the first space of the memory, and may activate a function for determining whether to remove at least one virtual frame obtained from the second plurality of points identified by LiDAR based on determining that the vehicle is traveling on a straight road using the virtual track stored in the second space. The virtual meta-object may include a rectangle formed by the first plurality of points obtained by LiDAR, and corresponds to an external object including a road sign. The virtual track may include a rectangle formed by a third plurality of points obtained at a time point different from a time point at which the virtual meta-object is generated.

[0186] In an example, the processor may identify whether the virtual meta-object and the converted virtual trajectory are associated with each other based on at least one of a distance between a first center point of the virtual meta-object and a second center point of the converted virtual trajectory, a ratio at which the virtual meta-object and the converted virtual trajectory overlap with each other, and any combination thereof.

[0187] In an example, the processor may overwrite the virtual track stored in the first space of the memory with the virtual metadata based on the virtual metadata and the converted virtual track being associated with each other.

[0188] In an example, the processor may recognize that the virtual meta-object and the converted virtual trajectory are not associated with each other, and may generate a second virtual trajectory different from the converted virtual trajectory as the first virtual trajectory using the virtual meta-object based on the presence of the virtual meta-object.

[0189] In an example, the processor may delete the virtual track stored in the memory based on the vehicle being driven on a road that is different from a straight road and includes at least one of curvature, slope, and any combination thereof.

[0190] In an example, the processor may delete the virtual track stored in the memory based on identifying at least one of the vertices forming the virtual track in a second area formed at a distance less than a first specified distance from the front of the vehicle.

[0191] In an example, the processor may activate a function for determining whether to remove at least one virtual frame obtained by LiDAR based on identifying at least one vertex among the vertices forming a virtual trajectory in a third area formed in a distance greater than or equal to a first specified distance from the front of the vehicle and below a second specified distance, the second specified distance being greater than the first specified distance.

[0192] In an example, the processor may deactivate a function for determining whether to remove at least one virtual track identified by the LiDAR based on identifying all vertices forming the virtual track in a fourth area greater than a second specified distance from the front of the vehicle.

[0193] In an example, the processor may determine whether to remove at least one virtual box based on at least one of whether virtual metadata exists, a shape formed by a second plurality of points contained in the at least one virtual box, a width of the at least one virtual box, a length of the at least one virtual box, a height of a highest point of the at least one virtual box, and any combination thereof.

[0194] In an example, the processor may determine whether at least one virtual frame and the converted virtual track are associated with each other based on the existence of a virtual meta-object, the shape formed by the second plurality of points contained in the at least one virtual frame being a specified shape, the width of the at least one virtual frame being less than the first reference length, the length of the at least one virtual frame being less than the first reference length, and the height of the highest point of the at least one virtual frame from the ground being greater than the second reference length, and may delete the at least one virtual frame based on the at least one virtual frame and the converted virtual track being associated with each other.

[0195] According to another aspect of the present disclosure, a vehicle control method may include: generating a virtual meta-object based on receiving information associated with a first plurality of points identified at a position above a first reference height from the ground through light detection and ranging (LiDAR); based on converting a virtual track stored in a first space of a memory to a time point at which the virtual meta-object is generated to obtain a converted virtual track, identifying whether the converted virtual track and the virtual meta-object are associated with each other; based on the virtual meta-object and the converted virtual track not being associated with each other, identifying whether the virtual meta-object exists; based on not generating a virtual meta-object due to not receiving information, determining whether a virtual track is identified in a first area formed at a distance of more than a first specified distance from the front of the vehicle; storing the virtual track identified in the first area in a second space different from the first space of the memory; and based on the vehicle being driven on a straight road, activating a function for determining whether to remove at least one virtual frame obtained from a second plurality of points identified by LiDAR using the virtual track stored in the second space. The virtual meta-object may include a rectangle formed by the first plurality of points obtained by LiDAR, and corresponds to an external object including a road sign. The virtual track may include a rectangle formed by a third plurality of points obtained at a time point different from the time point at which the virtual meta-object is generated.

[0196] The vehicle control method may also include: identifying whether the virtual meta-object and the converted virtual track are associated with each other based on at least one of a distance between a first center point of the virtual meta-object and a second center point of the converted virtual track, a ratio at which the virtual meta-object and the converted virtual track overlap with each other, and any combination thereof.

[0197] The vehicle control method further includes overwriting the virtual trajectory stored in the first space of the memory with the virtual metadata based on the virtual metadata and the converted virtual trajectory being associated with each other.

[0198] The vehicle control method may further include: recognizing that the virtual meta object and the converted virtual trajectory are not associated with each other; and generating a second virtual trajectory different from the converted virtual trajectory as the first virtual trajectory using the virtual meta object based on the existence of the virtual meta object.

[0199] The vehicle control method may further include: deleting the virtual track stored in the memory based on the vehicle being driven on a road that is different from a straight road and includes at least one of curvature, slope, and any combination thereof.

[0200] The vehicle control method may further include deleting the virtual track stored in the memory based on identifying at least one of the vertices forming the virtual track in a second area formed less than a first specified distance from the front of the vehicle.

[0201] The vehicle control method may also include: activating a function for determining whether to remove at least one virtual frame obtained by LiDAR based on identifying at least one vertex among the vertices forming the virtual trajectory in a third area formed at a distance greater than or equal to a first specified distance from the front of the vehicle and below a second specified distance, the second specified distance being greater than the first specified distance.

[0202] The vehicle control method may further include: based on identifying all vertices forming the virtual track in a fourth area greater than a second specified distance ahead of the vehicle, deactivating a function for determining whether to remove at least one virtual track identified by the LiDAR.

[0203] The vehicle control method may also include: determining whether to remove at least one virtual frame based on whether there is virtual metadata, a shape formed by multiple points contained in the at least one virtual frame, the width of the at least one virtual frame, the length of the at least one virtual frame, the height of the highest point of the at least one virtual frame, and at least one item of any combination thereof.

[0204] The vehicle control method may also include: determining whether at least one virtual frame and the virtual track are associated with each other based on the existence of a virtual element object, a shape formed by multiple points contained in at least one virtual frame is a specified shape, a width of at least one virtual frame is less than a first reference length, a length of at least one virtual frame is less than the first reference length, and a height of the highest point of at least one virtual frame from the ground is greater than a second reference length, and deleting at least one virtual frame based on the at least one virtual frame and the virtual track being associated with each other.

[0205] Figure 7 A computing system associated with a vehicle control device is shown.

[0206] refer to Figure 7 , the computing system 1000 may include at least one 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 , which are connected to each other via a bus 1200 .

[0207] The processor 1100 may be a central processing unit (CPU) or a semiconductor device for processing instructions stored in the memory 1300 and / or the storage 1600. The memory 1300 and the storage 1600 may include various types of volatile or non-volatile storage media. For example, the memory 1300 may include a read-only memory (ROM) 1310 and a random access memory (RAM) 1320.

[0208] Therefore, the operations of the methods or algorithms described in conjunction with the embodiments disclosed in the specification may be directly implemented by a hardware module, a software module, or a combination of a hardware module and a software module executed by the processor 1100. The software module may reside on a storage medium (i.e., memory 1300 and / or storage 1600) such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disks, removable disks, and CD-ROMs.

[0209] An exemplary storage medium may be coupled to the processor 1100. The processor 1100 may read information from the storage medium and may write information to the storage medium. Alternatively, the storage medium may be integrated with the processor 1100. The processor and the storage medium may reside in an application specific integrated circuit (ASIC). The ASIC may be located in a user terminal. In another case, the processor and the storage medium may reside in a user terminal as separate components.

[0210] This technology can eliminate virtual frames generated by noise.

[0211] Furthermore, the present technology can recognize noise generated by a road sign or a preceding vehicle, and can remove a virtual frame recognized as noise.

[0212] Furthermore, the present technology can remove a virtual frame recognized as noise to stably drive a vehicle control system associated with a vehicle control device.

[0213] Furthermore, various effects directly or indirectly determined by the present disclosure can be provided.

[0214] Although the present disclosure has been described above with reference to exemplary embodiments and the accompanying drawings, the present disclosure is not limited thereto but may be variously modified and changed by those skilled in the art without departing from the spirit and scope of the present invention as claimed in the following claims.

[0215] Therefore, the examples of the present disclosure are not intended to limit the technical spirit of the present disclosure, but are only for illustrative purposes. The scope of the present disclosure should be interpreted on the basis of the appended claims, and all technical ideas within the scope equivalent to the claims should be included in the scope of the present disclosure.

Claims

1. A vehicle control device, comprising: at least one sensor; Memory; and processor, Wherein, the processor is configured to: generating a virtual meta-object based on receiving information associated with a first plurality of points of the object, wherein the first plurality of points are identified by detection results of the at least one sensor and are located above a first reference height; determining whether a converted virtual trajectory is associated with the virtual meta-object, wherein the virtual trajectory stored in the first space of the memory is converted into a converted virtual trajectory corresponding to a time point at which the virtual meta-object is generated; determining whether the existence of the virtual meta-object is valid based on determining that the virtual meta-object and the converted virtual trajectory are not associated with each other; determining whether a virtual track is recognized in a first area formed at a distance spaced apart from the vehicle based on the virtual meta-object not being generated and the information not being received, wherein the distance is greater than a first distance; storing the virtual track identified in the first area in a second space different from the first space of the memory; and using the virtual track stored in the second space, determining whether to remove at least one virtual frame obtained from a second plurality of points identified from the detection result of the at least one sensor, wherein the virtual meta-object comprises a closed boundary formed by the first plurality of points, wherein the first plurality of points corresponds to an object comprising a landmark, and wherein the virtual trajectory includes a second closed boundary formed by a third plurality of points obtained at a time point different from a time point at which the virtual meta-object is generated, and wherein the second closed boundary corresponds to the object.

2. The vehicle control device according to claim 1, wherein: The processor is configured to: Based on at least one of a distance between a first center point of the virtual meta-object and a second center point of the converted virtual trajectory, a ratio at which the virtual meta-object and the converted virtual trajectory overlap with each other, and any combination thereof, it is determined whether the virtual meta-object and the converted virtual trajectory are associated with each other.

3. The vehicle control device according to claim 1, wherein: The processor is configured to: Based on determining that the virtual meta-object and the converted virtual trajectory are associated with each other, the virtual trajectory stored in the first space of the memory is overwritten with the virtual meta-object.

4. The vehicle control device according to claim 1, wherein: The processor is configured to: determining that the virtual meta-object and the converted virtual trajectory are not associated with each other; and Based on determining that the existence of the virtual meta-object is valid, a second virtual trajectory different from the converted virtual trajectory as the first virtual trajectory is generated using the virtual meta-object.

5. The vehicle control device according to claim 1, wherein: The processor is configured to: Based on determining that the vehicle is traveling on a road other than a straight road and including at least one of curvature, slope, and any combination thereof, the virtual track stored in the memory is deleted.

6. The vehicle control device according to claim 1, wherein: The processor is configured to: The virtual trajectory stored in the memory is deleted based on determining that at least one of the vertices forming the virtual trajectory is identified in a second area formed at a distance from the vehicle that is less than the first distance.

7. The vehicle control device according to claim 1, wherein: The processor is configured to: Based on determining that at least one of the vertices forming the virtual trajectory is identified in a third area formed at a second distance from the vehicle, determining whether to remove the at least one virtual frame obtained by the detection result of the at least one sensor using the virtual trajectory, wherein the second distance is greater than the first distance.

8. The vehicle control device according to claim 7, wherein: The processor is configured to: Based on all vertices forming the virtual track being identified in a fourth area spaced apart from the vehicle by a distance greater than the second distance, a function for determining whether to remove the virtual track identified by the detection result of the at least one sensor is deactivated.

9. The vehicle control device according to claim 7, wherein: The processor is configured to: Determine whether to remove the at least one virtual frame based on at least one of determining whether the existence of the virtual meta-object is valid, a shape formed by the second plurality of points contained in the at least one virtual frame, a width of the at least one virtual frame, a length of the at least one virtual frame, a height of the highest point of the at least one virtual frame, and any combination thereof.

10. The vehicle control device according to claim 9, wherein: The processor is configured to: determining whether the at least one virtual frame and the converted virtual track are associated with each other based on determining that the existence of the virtual meta-object is valid, the shape formed by the second plurality of points contained in the at least one virtual frame is a specified shape, the width of the at least one virtual frame is less than a first reference length, the length of the at least one virtual frame is less than the first reference length, and the height of the highest point of the at least one virtual frame from the ground is greater than a second reference length; as well as Based on determining that the at least one virtual frame and the converted virtual track are associated with each other, the at least one virtual frame is deleted.

11. A vehicle control method comprising the following steps: generating a virtual meta-object based on receiving information associated with a first plurality of points of the object, wherein the first plurality of points are identified by detection results of at least one sensor and are located above a first reference height; determining whether a converted virtual trajectory is associated with the virtual meta-object, wherein the virtual trajectory stored in the first space of the memory is converted into the converted virtual trajectory corresponding to the time point at which the virtual meta-object is generated; determining whether the existence of the virtual meta-object is valid based on determining that the virtual meta-object and the converted virtual trajectory are not associated with each other; determining whether a virtual track is recognized in a first area formed at a distance spaced apart from the vehicle based on the virtual meta-object not being generated and the information not being received, wherein the distance is greater than a first distance; storing the virtual track identified in the first area in a second space different from the first space of the memory; and using the virtual track stored in the second space, determining whether to remove at least one virtual frame obtained from a second plurality of points identified by the detection result of the at least one sensor, wherein the virtual meta-object comprises a closed boundary formed by the first plurality of points, wherein the first plurality of points corresponds to an object comprising a landmark, and wherein the virtual trajectory includes a second closed boundary formed by a third plurality of points obtained at a time point different from a time point at which the virtual meta-object is generated, and wherein the second closed boundary corresponds to the object.

12. The vehicle control method according to claim 11, further comprising the following steps: Based on at least one of a distance between a first center point of the virtual meta-object and a second center point of the converted virtual trajectory, a ratio at which the virtual meta-object and the converted virtual trajectory overlap with each other, and any combination thereof, it is determined whether the virtual meta-object and the converted virtual trajectory are associated with each other.

13. The vehicle control method according to claim 11, further comprising the following steps: Based on determining that the virtual meta-object and the converted virtual trajectory are associated with each other, the virtual trajectory stored in the first space of the memory is overwritten with the virtual meta-object.

14. The vehicle control method according to claim 11, further comprising the following steps: determining that the virtual meta-object and the converted virtual trajectory are not associated with each other; as well as Based on determining that the existence of the virtual meta-object is valid, a second virtual trajectory different from the converted virtual trajectory as the first virtual trajectory is generated using the virtual meta-object.

15. The vehicle control method according to claim 11, further comprising the following steps: Based on determining that the vehicle is traveling on a road other than a straight road and including at least one of curvature, slope, and any combination thereof, the virtual track stored in the memory is deleted.

16. The vehicle control method according to claim 11, further comprising the following steps: The virtual trajectory stored in the memory is deleted based on determining that at least one of the vertices forming the virtual trajectory is identified in a second area formed at a distance from the vehicle that is less than the first distance.

17. The vehicle control method according to claim 11, further comprising the following steps: Based on determining that at least one of the vertices forming the virtual trajectory is identified in a third area formed at a second distance from the vehicle, determining whether to remove the at least one virtual frame obtained by the detection result of the at least one sensor using the virtual trajectory.

18. The vehicle control method according to claim 17, further comprising the following steps: Based on all vertices forming the virtual track being identified in a fourth area spaced apart from the vehicle by a distance greater than the second distance, a function for determining whether to remove the virtual track identified by the detection result of the at least one sensor is deactivated.

19. The vehicle control method according to claim 17, further comprising the following steps: Determine whether to remove the at least one virtual frame based on at least one of determining whether the existence of the virtual meta-object is valid, a shape formed by multiple points contained in the at least one virtual frame, a width of the at least one virtual frame, a length of the at least one virtual frame, a height of the highest point of the at least one virtual frame, and any combination thereof.

20. The vehicle control method according to claim 19, further comprising the following steps: determining whether the at least one virtual frame and the virtual track are associated with each other based on determining that the existence of the virtual meta-object is valid, the shape formed by the plurality of points included in the at least one virtual frame is a specified shape, the width of the at least one virtual frame is less than a first reference length, the length of the at least one virtual frame is less than the first reference length, and the height of the highest point of the at least one virtual frame from the ground is greater than a second reference length; as well as Based on determining that the at least one virtual frame and the virtual track are associated with each other, the at least one virtual frame is deleted.

Images