Automatic driving control apparatus and method for generating driving

Abstract

The invention relates to an automatic driving control apparatus and a method for generating a driving path thereof. The automatic driving control device includes a processor that receives a travel path from a navigation device. The processor is configured to determine whether there is a turn section on the travel path, in response to determining that there is a turn section on the travel path, determine a turn path having a continuously changing curvature, and output the turn path.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] The present application claims priority to Korean Patent Application No. 10-2023-0094094 filed on Jul. 19, 2023, the entire contents of which application is incorporated herein for all purposes by this reference. Technical Field

[0003] The invention relates to an automatic driving control device and a method for generating a driving path thereof. Background Art

[0004] When generating a driving path of a vehicle, if a path with discontinuous curvature is generated, the steering angle of the vehicle must be adjusted to adapt to the discontinuous curvature after the vehicle stops, which is inconvenient. However, when following a continuous curvature path, the vehicle can follow a path with changing curvature without stopping.

[0005] A conventional method for generating a continuous curvature path is to construct the continuous curvature path using a clothoid that increases the curvature, a circle that maintains the increased curvature and changes the heading, and a clothoid that decreases the curvature to "0" again.

[0006] However, when the path ends at the end of the clothoid, the position where the end point will appear cannot be determined until all calculations are completed, so it is difficult to position the end point at the position desired by the user.

[0007] Two continuous curvature turning paths including two clothoids and a circle and line segment elements connecting the corresponding continuous curvature turning paths must be used. A turning path is constructed based on the starting point, and a turning path is constructed based on the end point, and the end clothoid parts of the two turning paths are connected by a straight line.

[0008] However, in this case, the path becomes very long and it is impossible to use the path in a narrow road section (for example, a U-turn section).

[0009] The information included in the Background of the Invention is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgment or any form of suggestion that this information forms the prior art already known to a person skilled in the art. Summary of the invention

[0010] Various aspects of the present invention are directed to providing an automatic driving control device and a method for generating a driving path thereof, so as to generate a continuous curvature path for a narrow turning section (eg, a U-turn section) when generating a driving path for a vehicle.

[0011] The technical problems to be solved by the present invention are not limited to the above-mentioned problems, and those skilled in the art to which the present invention belongs will clearly understand any other technical problems not mentioned herein from the following description.

[0012] According to one aspect of the present invention, an automatic driving control device may include a processor, the processor receiving a driving path from a navigation device, the processor being configured to determine whether there is a turning section on the driving path, and being configured to determine a turning path with a continuously changing curvature in response to determining that there is a turning section on the driving path, and being configured to output the turning path.

[0013] The processor is configured to determine a start point and an end point of a turning segment and a target vehicle heading deviation based on the driving path.

[0014] The processor may estimate a maximum curvature and a maximum steering angle velocity based on an end point of the turning segment and a target vehicle heading deviation.

[0015] The processor may estimate the maximum curvature and the maximum steering angular velocity using a deep neural network (DNN).

[0016] The processor is configured to determine an end point of the first clothoid curve and a vehicle heading and curvature at the end point of the first clothoid curve based on the maximum curvature and the maximum steering angle velocity.

[0017] The processor is configured to determine a swivel length based on the maximum curvature and the maximum steering angle velocity.

[0018] The processor is configured to determine a vehicle heading deviation in a clothoid interval based on a maximum curvature and a maximum steering angle velocity.

[0019] The processor is configured to determine a rotation center point based on an end point of the first clothoid curve, a vehicle heading at the end point of the first clothoid curve, and a maximum curvature, and can be configured to determine a circular curve based on an end point of the first clothoid curve, a target vehicle heading deviation, a vehicle heading deviation in a clothoid interval, and a rotation center point.

[0020] The processor is configured to determine a second clothoid curve based on the target vehicle heading deviation and the rotation center point.

[0021] The processor is configured to determine a turning path using a first clothoid curve, a circular curve, and a second clothoid curve.

[0022] According to another aspect of the present invention, a method for generating a driving path of an automatic driving control device may include: receiving the driving path from a navigation device, determining whether there is a turning section on the driving path, in response to determining that there is a turning section on the driving path, determining a turning path with continuously changing curvature, and outputting the turning path.

[0023] Determining the turning path may include determining a start point and an end point of the turning section and a heading deviation of the target vehicle based on the driving path.

[0024] Determining the turning path may further include estimating a maximum curvature and a maximum steering angle velocity based on an end point of the turning segment and the target vehicle heading deviation.

[0025] Estimating the maximum curvature and the maximum steering angular velocity may include estimating the maximum curvature and the maximum steering angular velocity using a deep neural network (DNN).

[0026] Determining the turning path may further include determining an end point of the first clothoid curve and a vehicle heading and a curvature at the end point of the first clothoid curve based on the maximum curvature and the maximum steering angle velocity.

[0027] Determining the turning path may further include determining a turn length based on the maximum curvature and the maximum steering angle velocity.

[0028] Determining the turning path may further include determining a vehicle heading deviation in the clothoid interval based on the maximum curvature and the maximum steering angle velocity.

[0029] Determining the turning path may further include determining a rotation center point based on an end point of the first clothoid curve, a vehicle heading at the end point of the first clothoid curve, and a maximum curvature, and determining a circular curve based on an end point of the first clothoid curve, a target vehicle heading deviation, a vehicle heading deviation in the clothoid interval, and a rotation center point.

[0030] Determining the turning path may further include determining a second clothoid curve based on the target vehicle heading deviation and the rotation center point.

[0031] Determining the turning path may further include determining the turning path using a first clothoid curve, a circular curve, and a second clothoid curve.

[0032] The methods and apparatus of the present invention have other features and advantages, which will be apparent from, or will be described in more detail in, the accompanying drawings and the following detailed description incorporated herein, which together serve to explain the specific principles of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a block diagram showing a configuration of an automatic driving control device according to various exemplary embodiments of the present invention;

[0034] Figure 2 is a schematic diagram for describing a process of generating a driving path according to various exemplary embodiments of the present invention;

[0035] Figure 3 is a graph showing a change in a turning path according to a change in curvature associated with the present invention;

[0036] Figure 4 is a graph showing a change in a turning path according to a change in a steering angular speed related to the present invention;

[0037] Figure 5 A deep neural network (DNN) structure according to various exemplary embodiments of the present invention is shown;

[0038] Figure 6 is a schematic diagram showing examples of density contours according to various exemplary embodiments of the present invention;

[0039] Figure 7 is a schematic diagram showing an example of estimating parameters using a DNN according to various exemplary embodiments of the present invention;

[0040] Figure 8 is a flowchart illustrating a method for generating a driving path of an automatic driving control device according to various exemplary embodiments of the present invention;

[0041] Fig. 9 is a flowchart illustrating a method for generating a turning path according to various exemplary embodiments of the present invention; and

[0042] Fig.10 Examples of generating a turning path according to various exemplary embodiments of the present invention are shown.

[0043] It should be understood that the accompanying drawings are not necessarily drawn to scale, but are appropriately simplified drawings of various features presented to illustrate the basic principles of the present invention. The predetermined design features of the present invention as included herein (e.g., including specific dimensions, directions, positions and shapes) will be determined in part by the specific intended application and use environment.

[0044] In the drawings, like reference numerals refer to the same or equivalent parts of the present invention throughout the several figures of the drawing. DETAILED DESCRIPTION

[0045] Reference will now be made in detail to various embodiments of the present invention, examples of which are illustrated in the accompanying drawings and described below. Although the present invention will be described in conjunction with exemplary embodiments of the present invention, it should be understood that this specification is not intended to limit the present invention to those exemplary embodiments of the present invention. On the other hand, the present invention is intended to cover not only the exemplary embodiments of the present invention, but also various alternative embodiments, modified embodiments, equivalent embodiments or other embodiments that may be included in the spirit and scope of the present invention as defined by the appended claims.

[0046] Hereinafter, various exemplary embodiments of the present invention will be described in detail with reference to the exemplary drawings. In the accompanying drawings, the same reference numerals will be used throughout to represent the same or equivalent elements. In addition, detailed descriptions of well-known features or functions will be excluded to avoid unnecessarily obscuring the subject matter of the present invention.

[0047] When describing components of exemplary embodiments of the present invention, terms such as first, second, "A", "B", (a), (b), etc. may be used. These terms are used only to distinguish one element from another, but do not limit the corresponding elements, regardless of the order or priority of the corresponding elements. In addition, unless otherwise defined, all terms (including technical and scientific terms) used in this article are interpreted according to the conventions of the art to which the present invention belongs. It will be understood that the terms used in this article should be interpreted as having a meaning consistent with the meaning in the context of the present invention and related fields, and should not be interpreted as idealized or overly formalized meanings unless clearly defined in this article.

[0048] Figure 1 is a block diagram illustrating a configuration of an automatic driving control device according to various exemplary embodiments of the present invention. Figure 2 is a schematic diagram for describing a process of generating a driving path according to various exemplary embodiments of the present invention.

[0049] refer to Figure 1 The automatic driving control device 100 may include a navigation device 110, a detection device 120, a memory 130, a communication device 140 and / or a processor 150.

[0050] When a destination is set, the navigation device 110 can navigate a driving path from a starting point (e.g., the current location of the vehicle) to the destination, and can guide the vehicle along the navigated driving path. The navigation device 110 can reflect real-time traffic information when navigating the driving path to search for an optimal path (e.g., the shortest distance and / or the shortest time, etc.). Although not shown in the drawings, the navigation device 110 may include a memory for storing map data, a global positioning system (GPS) receiver configured to measure the location of the vehicle, a communication module for receiving traffic information from the outside, and / or a processor for navigating the driving path and guiding the vehicle along the navigated driving path, etc.

[0051] The detection device 120 can obtain driving information (e.g., steering angle or vehicle speed, etc.) by using sensors installed on the vehicle (e.g., steering angle sensor, vehicle speed sensor, inertial measurement unit (IMU) and / or image sensor, etc.).

[0052] The memory 130 may store specification information and / or predetermined information of the vehicle. The memory 130 may include a turn end point determination logic, a continuous curvature path generation algorithm, and / or a deep learning algorithm, etc.

[0053] The memory 130 may be a non-volatile storage medium that stores instructions executed by the processor 150. The memory 130 may be implemented as at least one of a storage medium (or recording medium) such as a flash memory, a hard disk, a solid state drive (SSD), a random access memory (RAM), a static RAM (SRAM), a read-only memory (ROM), a programmable ROM (PROM), an electrically erasable programmable ROM (EEPROM), or an erasable programmable ROM (EPROM).

[0054] The communication device 140 can support the establishment of a wired or wireless communication connection between the automatic driving control device 100 and an external electronic device (e.g., an electronic control unit (ECU) etc.), and communicate through the established connection. The communication device 140 may include a communication processor, a communication circuit, an antenna and / or a transceiver etc. In an exemplary embodiment of the present invention, the wireless communication includes a technology using radio waves.

[0055] The processor 150 may be operably connected to the navigation device 110, the detection device 120, the memory 130, and / or the communication device 140 through a bus. The processor 150 may communicate with the navigation device 110, the detection device 120, the memory 130, and / or the communication device 140 to control the overall operation of the automatic driving control device 100. The processor 150 may be implemented as at least one of a processing device such as an application specific integrated circuit (ASIC), a digital signal processor (DSP), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a microcontroller, or a microprocessor.

[0056] The processor 150 may receive a driving path from the navigation device 110. The processor 150 may identify whether there is a turning section (e.g., a U-turn section) ahead of the vehicle based on the received driving path. The processor 150 may identify whether there is a turning section within a predetermined distance (e.g., 20 m) ahead of the vehicle on the driving path.

[0057] When the existence of a turning section is identified, the processor 150 may be configured to generate a turning path for the turning section. The processor 150 may be configured to generate a turning path including two clothoid curves (or clothoid paths) and a circular curve (or circular path). The turning path may be a path with a continuously changing curvature, i.e., a continuous curvature path.

[0058] The processor 150 may output the generated turning path to the navigation device 110 and / or the vehicle controller. The navigation device 110 may display the turning path on its display screen so that the driver can drive the vehicle along the turning path. The vehicle controller may be configured to control the behavior of the vehicle (e.g., steering, braking, acceleration and / or deceleration, etc.) so that the vehicle follows the turning path.

[0059] Hereinafter, a description will be given of a process of generating a turning path.

[0060] The processor 150 may identify the starting point q of the turning segment based on the driving path received from the navigation device 110. s and the end point (or target point) q g The processor 150 may be configured to determine the end point q of the turning segment using the turning end point determination logic. g The end point of the turning section is q g It can be the center coordinates of the lane to be turned and converged.

[0061] The processor 150 may be based on the end point q of the turning segment. g and the target vehicle heading deviation δ to estimate the maximum curvature k max and the maximum steering angular velocity σ max At this time, the processor 150 can use a deep neural network (DNN) to estimate the maximum curvature k max and the maximum steering angular velocity σ max . k max is the reciprocal of the turning radius of the vehicle when the vehicle steering wheel is adjusted to the maximum steering angle, σ max The target vehicle heading deviation δ is the heading of the vehicle required to reach the target point (or end point) of the turning section, which can be the difference between the vehicle heading at the start point of the turning section and the vehicle heading at the end point of the turning section.

[0062] The processor 150 may be configured to calculate the maximum curvature k based on the max and the maximum steering angular velocity σ max To determine the heading δ of the vehicle configured to vary using the clothoid interval min (i.e., the vehicle heading deviation in the roundabout interval) and the roundabout length s. min It can be expressed as the following equation 1, and s can be expressed as the following equation 2.

[0063] [Equation 1]

[0064]

[0065] [Equation 2]

[0066]

[0067] The processor 150 may be configured to calculate the maximum curvature k based on the max and the maximum steering angular velocity σ max Determine the first clothoid curve. The processor 150 may be configured to determine the first clothoid curve using the following equation 3, where the starting point q of the turning section is s is the starting point of the first clothoid curve.

[0068] [Equation 3]

[0069] in,

[0070] Among them, q i represents the end point of the first clothoid curve (x i ,y i ), θ i represents the vehicle heading at the end point of the first clothoid curve, k i represents the curvature at the end point of the first clothoid curve, C f (x) and S f (x) represents the Fresnel integral value. f (x) and S f (x) can be expressed as the following equation 4 and the following equation 5, respectively.

[0071] [Equation 4]

[0072]

[0073] [Equation 5]

[0074]

[0075] Wherein, u represents a predetermined time variable.

[0076] From the starting point of the first clothoid curve (i.e., the starting point of the turning section q s ) to the end point q of the first clothoid i The points formed can have randomly set intervals. Parameters used to determine the Fresnel integration interval The curvature k can be increased from "0" to k max .

[0077] The processor 150 may be configured to determine the end point q of the first clothoid curve based on the end point q of the first clothoid curve. i and the maximum curvature k max The rotation center point Ω of the circular curve is determined. The rotation center point of the circular curve can be expressed as the following equation 6.

[0078] [Equation 6]

[0079]

[0080] The processor 150 may be configured to determine the radius r of the circular curve using the rotation center point Ω. The radius r of the circular curve may be expressed as Equation 7 below.

[0081] [Equation 7]

[0082]

[0083] The processor 150 may be configured to determine the end point q of the circular curve j The processor 150 may be configured to determine the end point q of the circular curve using the following equation 8: j and the end point q j The vehicle heading at θ j and curvature k j .

[0084] [Equation 8]

[0085]

[0086] The processor 150 may be configured to determine the end point q of the circular curve. j To the target point q of the turning section g At this time, the processor 150 can be configured to determine the end point of the second clothoid curve (ie, the target point q of the turning section) using the following equation 9: g ) and the vehicle heading θ at the end point j and curvature k g .

[0087] [Equation 9]

[0088]

[0089] Where μ represents the radius r (i.e., the distance between the rotation center Ω and the starting point q of the turning section) with the rotation center Ω as the reference. s The distance between The point on the curve (i.e., the starting point of the curve s ) and the starting point q of the turning section s The angle formed by the tangent line L2 at Ω / y Ω ).

[0090] The processor 150 may be configured to generate a turning path including a first clothoid curve, a circular curve, and a second clothoid curve. In other words, the processor 150 may connect the end point of the first clothoid curve with the start point of the circular curve, and may connect the end point of the circular curve with the start point of the second clothoid curve to generate a continuous curvature path.

[0091] Figure 3 is a graph showing a change in a turning path according to a change in curvature related to the present invention. Figure 4 is a graph showing a change in a turning path according to a change in a steering angle speed related to the present invention.

[0092] refer to Figure 3 , it can be seen that with the maximum curvature k max As the value increases, the turning radius of the turning path decreases. Figure 4 , it can be seen that with the maximum steering angular velocity σ max As the maximum curvature k increases, the turning radius of the turning path decreases. max and the maximum steering angular velocity σ max Affects the turning radius of the turning path, so they can be selected as variables needed to determine the end point of the turning path.

[0093] In order to determine the end point q of the turning path g , the possible range of the continuous curvature path according to the constraints of the vehicle (e.g., steering angle velocity and maximum steering angle, etc.) can be determined, and the curvatures k, σ, and δ reaching a specific end point (x, y) can be collected to make the following Table 1. However, when using Table 1, the following problems may occur.

[0094] 1) Since k and σ are searched using x, y, and δ, calculations equivalent to the product of the number of parameters are performed, thereby wasting unnecessary computational resources.

[0095] 2) Since x, y, and δ are not arranged continuously, an empty space (i.e., a space where the search fails) is generated, and a continuous curvature path cannot be generated.

[0096] [Table 1]

[0097] x,y,δ k,σ <![CDATA[x 1 ,y 1 ,d 1 ]]> <![CDATA[k 1 ,s 1 ]]> <![CDATA[x 2 ,y 2 ,d 2 ]]> <![CDATA[k 2 ,s 2 ]]> … …

[0098] In order to solve the problem of generating a continuous curvature path using the above Table 1, a deep neural network (DNN) is configured to generate a function that can approximate Table 1.

[0099] Figure 5 DNN structures according to various exemplary embodiments of the present invention are shown. Figure 6 is a schematic diagram illustrating examples of isodensities according to various exemplary embodiments of the present invention.

[0100] The DNN can receive the end point (x, y) of the turning path and the target vehicle heading deviation δ as input data, and can output the maximum curvature k max and the maximum steering angular velocity σ max As output data. The hidden layer of DNN can be 64*3, which can be changed according to the situation. The activation function of each layer can use an activation function for solving regression problems, for example, a sigmoid function, a hyperbolic tangent (tanh) function, an exponential linear unit (ELU) function, and / or a linear rectification (ReLU) function.

[0101] When Figure 3 When the points are concentrated near the starting point of the turning path as shown in Figure 6 Construct isodensities as shown to evenly distribute points in dense areas.

[0102] Figure 7 is a schematic diagram illustrating an example of estimating parameters using a DNN according to various exemplary embodiments of the present invention.

[0103] The processor 150 may input the target vehicle heading deviation δ and the end point (x, y) of the turning path into the DNN. For example, the processor 150 may input δ (= 33 [degrees]), x (= 2.956708 [m]) and y (= 0.875817 [m]) into the DNN, and may estimate the maximum curvature k max and the maximum steering angular velocity σ max .

[0104] Thereafter, the processor 150 may be configured to utilize the estimated maximum curvature k max and the maximum steering angular velocity σ max Generates a continuous curvature path (ie, a turning path).

[0105] Figure 8 is a flowchart illustrating a method for generating a driving path of an automatic driving control device according to various exemplary embodiments of the present invention.

[0106] In step S100, the processor 150 may receive a driving path from the navigation device 110. The navigation device 110 may navigate a driving path from a starting point of the vehicle to a destination of the vehicle, and may send the navigated driving path to the processor 150. The processor 150 may be configured to generate a local path based on the driving path (i.e., a global path) received from the navigation device 110.

[0107] In step S110, the processor 150 may be configured to determine whether there is a turning section based on the driving path. The processor 150 may identify whether there is a turning section ahead of the vehicle based on the received driving path. The processor 150 may identify whether there is a turning section within a predetermined distance ahead of the vehicle on the driving path (or partial path).

[0108] When it is determined that there is a turning section on the driving path, in step S120, the processor 150 may be configured to generate a turning path. The processor 150 may be configured to generate a turning path including two clothoid curves and one circular curve. The turning path may be a continuous curvature path with a continuously changing curvature.

[0109] In step S130, the processor 150 may output the generated turning path. The processor 150 may output the generated turning path to the navigation device 110 and / or the vehicle controller. The navigation device 110 may display the turning path on its display screen, and the driver of the vehicle may control the steering wheel of the vehicle so that the vehicle travels along the turning path. The vehicle controller may be configured to control the behavior of the vehicle (e.g., steering, braking, acceleration and / or deceleration, etc.) so that the vehicle (e.g., an autonomous driving vehicle) follows the turning path.

[0110] Fig. 9 is a flow chart illustrating a method for generating a turning path according to various exemplary embodiments of the present invention.

[0111] In step S200, the processor 150 may be configured to determine the start and end of the turn segment identified on the driving path. The processor 150 may be configured to determine the end of the turn segment using turn end determination logic. In addition, the processor 150 may be configured to determine the difference between the vehicle heading at the start of the turn segment and the vehicle heading at the end of the turn segment, i.e., the target vehicle heading deviation (or displacement).

[0112] The processor 150 may estimate the maximum curvature and the maximum steering angular velocity based on the end point of the turning section and the target vehicle heading deviation. The processor 150 may estimate the maximum curvature and the maximum steering angular velocity using a DNN. In other words, the processor 150 may input the end point of the turning section and the target vehicle heading deviation into the DNN, and may output the maximum curvature and the maximum steering angular velocity determined based on the end point of the turning section and the target vehicle heading deviation in the DNN.

[0113] In step S220, the processor 150 may be configured to determine a first clothoid curve based on the starting point of the turning section, the maximum curvature, and the maximum steering angle velocity. The first clothoid curve may use the starting point of the turning section as its starting point. The processor 150 may be configured to determine the end point of the first clothoid curve and the vehicle heading and curvature at the end point using equations 3 to 5 above. In addition, the processor 150 may be configured to increase the curvature from "0" to the maximum curvature k max , and determine the first clothoid curve at the same time.

[0114] In step S230, the processor 150 may be configured to determine a circular curve starting from the end point of the first clothoid curve based on the heading of the vehicle (which may be changed using the end point of the first clothoid curve, the maximum curvature, and the clothoid interval). The processor 150 may be configured to determine the rotation center point according to the above equation 6 using the end point of the first clothoid curve (i.e., the starting point of the circular curve) and the maximum curvature. The processor 150 may be configured to determine the circular curve using the end point of the first clothoid curve, the target vehicle heading deviation, the vehicle heading deviation in the clothoid interval, and the rotation center point.

[0115] In step S240, the processor 150 may be configured to determine the second clothoid interval based on the rotation center point, the target vehicle heading deviation, and the vehicle heading deviation in the clothoid interval. The second clothoid curve may be a path constructed from the end point of the circular curve to the target point of the turning section. The processor 150 may be configured to determine the end point of the second clothoid curve (i.e., the target point of the turning section) and the vehicle heading and curvature at the end point using equation 9 above.

[0116] In step S250, the processor 150 may be configured to generate a turning path including a first clothoid curve, a circular curve, and a second clothoid curve. The processor 150 may connect the end point of the first clothoid curve with the start point of the circular curve, and may connect the end point of the circular curve with the start point of the second clothoid curve to generate a continuous curvature path.

[0117] Fig.10 Examples of generating a turning path according to various exemplary embodiments of the present invention are shown.

[0118] refer to Fig.10 , it can be seen that a U-turn distance of 8.5 m is required. Since the U-turn distance is reduced by 1.5 m compared with the prior art, a U-turn can be made in the third lane. Compared with the prior art, the automatic driving control device 100 can enable the vehicle to achieve a U-turn of a shorter distance.

[0119] The autonomous driving control device 100 can be configured to generate a turning path with continuous curvature, thereby preventing unnecessary stops of the vehicle. In addition, the autonomous driving control device 100 can be configured to generate a path that reflects the non-holonomic constraints of the actual vehicle, thereby satisfying the vehicle kinematics and promoting smooth driving.

[0120] Embodiments of the present invention can construct a continuous curvature path using two clothoid curves and one circular curve, and can provide the continuous curvature path so that a vehicle does not stop at a narrow turning section (eg, a U-turn section) and turns smoothly along the continuous curvature path.

[0121] In addition, terms related to control devices such as "controller", "control device", "control unit", "control means", "control module" or "server" refer to hardware devices including a memory and a processor configured to execute one or more steps interpreted as an algorithm structure. The memory stores the algorithm steps, and the processor executes the algorithm steps to perform one or more processes of the method according to various exemplary embodiments of the present invention. The control device according to the exemplary embodiment of the present invention can be implemented by a non-volatile memory and a processor, the non-volatile memory is configured to store an algorithm for controlling the operation of various components of the vehicle or data about software instructions for executing the algorithm, and the processor is configured to perform the above operations using data stored in the memory. The memory and the processor may be separate chips. Alternatively, the memory and the processor may be integrated in a single chip. The processor may be implemented as one or more processors. The processor may include various logic circuits and operation circuits, may be configured to process data according to a program provided from the memory, and may be configured to generate a control signal according to the processing result.

[0122] The control device may be at least one microprocessor operated by a predetermined program, which may include a series of instructions for executing the methods included in the aforementioned various exemplary embodiments of the present invention.

[0123] The foregoing invention may also be implemented as a computer-readable code on a computer-readable recording medium. A computer-readable recording medium is any data storage device capable of storing data that can be subsequently read by a computer system and storing and executing program instructions that can subsequently be read by a computer system. Examples of computer-readable recording media include hard disk drives (HDDs), solid-state disks (SSDs), silicon disk drives (SDDs), read-only memories (ROMs), random access memories (RAMs), CD-ROMs, magnetic tapes, floppy disks, optical data storage devices, and the like, as well as being implemented as carrier waves (e.g., transmitted over the Internet). Examples of program instructions include machine language codes (e.g., machine language codes generated by a compiler) and high-level language codes that can be executed by a computer using an interpreter, etc.

[0124] In various exemplary embodiments of the present invention, each of the above-described operations may be performed by a control device, and the control device may be configured by a plurality of control devices or an integrated single control device.

[0125] In various exemplary embodiments of the present invention, the memory and the processor may be provided as one chip, or provided as separate chips.

[0126] In various exemplary embodiments of the present invention, the scope of the present invention includes software or machine-executable instructions (e.g., operating systems, applications, firmware, programs, etc.) for enabling operations of methods according to various embodiments to be performed on a device or computer, and non-transitory computer-readable media including such software or commands stored thereon and capable of being executed on a device or computer.

[0127] In various exemplary embodiments of the present invention, the control device may be implemented in the form of hardware or software, or may be implemented as a combination of hardware and software.

[0128] Furthermore, terms such as “unit”, “module” and the like included in the specification refer to a unit for processing at least one function or operation, which may be implemented by hardware, software or a combination thereof.

[0129] In an exemplary embodiment of the present invention, a vehicle may refer to a concept based on various vehicles. In some cases, a vehicle may be interpreted as a concept based on various land vehicles (e.g., cars, motorcycles, trucks, and buses) traveling on a road, as well as various vehicles such as airplanes, drones, ships, etc.

[0130] For ease of interpretation and accurate definition in the appended claims, the terms "upper", "lower", "inner", "outer", "upward", "downward", "upwardly", "downwardly", "front", "rear", "back", "inside", "outside", "inwardly", "outwardly", "inner", "external", "inwardly", "outwardly", "forward" and "rearward" are used to describe the features of the exemplary embodiments with reference to the positions of such features as shown in the accompanying drawings. It will be further understood that the term "connected" or its derivatives refer to both direct and indirect connections.

[0131] The term "and / or" may include a combination of multiple related listed items or any one of multiple related listed items. For example, "A and / or B" includes all three situations such as "A", "B" and "A and B".

[0132] In this specification, a singular expression includes a plural expression unless the context clearly indicates otherwise.

[0133] In an exemplary embodiment of the present invention, “at least one of A and B” may refer to “at least one of A or B” or “at least one of a combination of at least one of A and B”. Furthermore, “one or more of A and B” may refer to “one or more of A or B” or “one or more of a combination of one or more of A and B”.

[0134] In the exemplary embodiments of the present invention, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, values, steps, operations, elements, parts, or a combination thereof described in the specification, and do not exclude the possibility of adding or existing one or more other features, values, steps, operations, elements, parts, or a combination thereof.

[0135] According to the exemplary embodiments of the present invention, components may be combined with each other to be implemented as one, or some components may be omitted.

[0136] The foregoing descriptions of specific exemplary embodiments of the present invention are presented for the purpose of illustration and description. These descriptions are not intended to be exhaustive or to limit the present invention to the precise form disclosed, and it is apparent that many modifications and changes may be made in light of the foregoing teachings. Exemplary embodiments are selected and described to explain the specific principles of the present invention and their practical application, so that other persons skilled in the art can implement and utilize various exemplary embodiments of the present invention and various alternative and modified embodiments thereof. The scope of the present invention is intended to be limited by the appended claims and their equivalents.

Claims

1. An automatic driving control device, comprising: a processor configured to receive a travel path from a navigation device operatively connected to the processor, Wherein, the processor is configured as follows: Determining whether there is a turning section on the driving path; In response to determining that there is a turning section on the driving path, determining a turning path with a continuously changing curvature; The turning path is output.

2. The automatic driving control device according to claim 1, wherein: The processor is further configured to determine a start point and an end point of the turning section and a heading deviation of the target vehicle based on the driving path.

3. The automatic driving control device according to claim 2, wherein: The processor is further configured to estimate a maximum curvature and a maximum steering angular velocity based on an end point of the turning segment and a target vehicle heading deviation.

4. The automatic driving control device according to claim 3, wherein: The processor is further configured to estimate the maximum curvature and the maximum steering angular velocity using a deep neural network.

5. The automatic driving control device according to claim 3, wherein: The processor is further configured to determine an end point of the first clothoid curve and a vehicle heading and a curvature at the end point of the first clothoid curve based on the maximum curvature and the maximum steering angle velocity.

6. The automatic driving control device according to claim 5, wherein: The processor is further configured to determine a swivel length based on the maximum curvature and the maximum steering angle velocity.

7. The automatic driving control device according to claim 6, wherein: The processor is further configured to determine a vehicle heading deviation in a clothoid interval based on the maximum curvature and the maximum steering angle velocity.

8. The automatic driving control device according to claim 7, wherein: The processor is further configured to: determining a rotation center point based on an end point of the first clothoid curve, a vehicle heading at the end point of the first clothoid curve, and a maximum curvature; A circular curve is determined based on an end point of the first clothoid curve, a target vehicle heading deviation, a vehicle heading deviation in the clothoid interval, and a rotation center point.

9. The automatic driving control device according to claim 8, wherein: The processor is further configured to determine a second clothoid curve based on the target vehicle heading deviation and the rotation center point.

10. The automatic driving control device according to claim 9, wherein: The processor is further configured to determine the turning path using a first clothoid curve, a circular curve, and a second clothoid curve.

11. A method for generating a driving path of an automatic driving control device, the method comprising: receiving, by a processor, a driving route from a navigation device; Determining, by a processor, whether there is a turning section on the driving path; In response to determining that there is a turning section on the driving path, the processor determines a turning path with a continuously changing curvature; The turning path is output by a processor.

12. The method according to claim 11, wherein: Determining the turning path includes: The starting point and the end point of the turning section and the target vehicle heading deviation are determined based on the driving path.

13. The method according to claim 12, wherein: Determining the turning path further includes: A maximum curvature and a maximum steering angular velocity are estimated based on an end point of the turning segment and a target vehicle heading deviation.

14. The method according to claim 13, wherein: Estimation of the maximum curvature and maximum steering angular velocity includes: Estimation of maximum curvature and maximum steering angular velocity using deep neural networks.

15. The method according to claim 13, wherein: Determining the turning path further includes: An end point of the first clothoid curve and a vehicle heading and a curvature at the end point of the first clothoid curve are determined based on the maximum curvature and the maximum steering angle velocity.

16. The method according to claim 15, wherein: Determining the turning path further includes: The swing length is determined based on the maximum curvature and the maximum steering angle velocity.

17. The method according to claim 16, wherein: Determining the turning path further includes: The vehicle heading deviation in the clothoid interval is determined based on the maximum curvature and the maximum steering angle velocity.

18. The method according to claim 17, wherein: Determining the turning path further includes: determining a rotation center point based on an end point of the first clothoid curve, a vehicle heading at the end point of the first clothoid curve, and a maximum curvature; A circular curve is determined based on an end point of the first clothoid curve, a target vehicle heading deviation, a vehicle heading deviation in the clothoid interval, and a rotation center point.

19. The method according to claim 18, wherein: Determining the turning path further includes: A second clothoid curve is determined based on the target vehicle heading deviation and the rotation center point.

20. The method according to claim 19, wherein: Determining the turning path further includes: The turning path is determined using a first clothoid curve, a circular curve, and a second clothoid curve.

Images