Vehicle and Its Control Method

Abstract

The present invention relates to a vehicle and a control method thereof. The vehicle avoids a collision with a target object by predicting an expected travel path of the target object located in front of the vehicle. The vehicle also predicts a possibility of a collision with the target object.

Description

[0001] Cross - reference to related applications

[0002] This application claims the priority benefit of Korean Patent Application No. 10 - 2020 - 0071074, filed on Jun. 11, 2020, with the Korean Intellectual Property Office, the entire contents of which are incorporated herein by reference. Technical field

[0003] The present invention relates to a vehicle that avoids collisions by predicting the driving path of a vehicle located in front of the vehicle and a method of controlling the vehicle. Background art

[0004] Recently, as autonomous driving has been attracting attention to provide convenience to drivers, various types of advanced driver assistance systems (ADAS) have been developed. Specifically, since the autonomous driving market is expected to enter a growth trend, research on autonomous driving is being actively conducted.

[0005] For example, Adaptive Cruise Control (ACC) is being actively studied. ACC is a system that allows a vehicle to travel while maintaining a speed without driver manipulation when the driver sets a desired speed. When there is a target object in front of the vehicle, a collision can be avoided by only predicting the expected driving path of the target vehicle. Summary of the invention

[0006] Accordingly, an object of the present invention is to provide a vehicle and a control method thereof that can avoid a collision with a target object by predicting the expected driving path of the target object located in front of the vehicle and predicting the possibility of a collision with the target object.

[0007] Other aspects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the present invention. According to one aspect of the present invention, a vehicle may include: a first sensor unit configured to acquire vehicle driving information, the vehicle driving information including position information, speed information, and heading direction information of the vehicle; a second sensor unit configured to acquire target object driving information, the target object driving information including position information, speed information, heading value information of the target object, and road information around the vehicle; a controller configured to: predict an expected driving path of the vehicle based on the vehicle driving information; determine the reliability of the expected driving path of the vehicle based on a learning table, the learning table being generated by learning based on the expected driving path of the vehicle, global positioning system (GPS) data of the vehicle, and internal signals of the vehicle; when the reliability of the expected driving path of the vehicle is greater than or equal to a predetermined threshold, predict an expected driving path of the target object in real time based on the target object driving information; and operate the vehicle based on the expected driving path of the vehicle and the determined expected driving path of the target object to avoid a collision between the vehicle and the target object.

[0008] The controller may be configured to predict an absolute speed of the target object based on information acquired by the first sensor unit and information acquired by the second sensor unit. The second sensor unit may include a camera, a radar, and a lidar. The controller may be configured to: determine a first heading value of the target object based on the position of the target object, using at least one of the camera, the radar, or the lidar included in the second sensor unit; determine a second heading value of the target object based on the absolute speed; and predict a heading direction of the target object based on the first heading value and the second heading value of the target object.

[0009] The controller may be configured to: calculate an offset between the target object and the expected driving path based on the expected driving path of the vehicle and the position information of the target object; when the offset is less than a predetermined first value, determine a point on the expected driving path closest to the target object as a collision point; and when a time difference between the vehicle and the target object reaching the collision point is less than a predetermined second value, operate the vehicle to avoid a collision with the target object.

[0010] The surrounding road information of the vehicle may include lane line information on both sides of the vehicle, and the controller may be configured to: calculate an offset between the left lane line or the right lane line of the lane line information on both sides of the vehicle and the target object; predict a second collision point between the vehicle and the target object when the offset is less than a predetermined first value; and operate the driving unit to avoid a collision with the target object when the time difference between the vehicle and the target object reaching the second collision point is less than a predetermined second value. The controller may be configured to: determine a weight related to the longitudinal absolute speed of the target object according to the position of the target object; and determine the longitudinal movement direction of the target object based on the absolute speed of the target object acquired from a predetermined previous time point, the absolute speed of the target object at the current time point, and the weight.

[0011] The controller may be configured to: calculate a reference value based on the lateral absolute speed of the target object and the orientation direction of the target object, and in response to determining that the reference value is greater than or equal to a predetermined third value, determine that the target object performs a lateral movement based on the absolute speed of the target object acquired from a predetermined previous time point, the absolute speed of the target object at the current time point, and the information acquired from the first sensor unit.

[0012] The controller may be configured to: calculate a change amount of the orientation direction of the target object; calculate a change amount of the orientation of the target object acquired from a predetermined previous time point, and determine whether the target object maintains the orientation direction based on the change amount of the orientation direction of the target object and the change amount of the orientation of the target object acquired from a predetermined previous time point. The controller may be configured to: determine whether the offset between the target object and the expected driving path of the vehicle remains constant based on the change amount of the offset between the target object and the left lane line Lh or the right lane line Rh of the lane line information on both sides of the vehicle acquired from a predetermined previous time point and the change amount of the offset between the target object and the left lane line or the right lane line of the vehicle acquired at the current time point.

[0013] The controller may be configured to: calculate a change amount of the orientation direction of the target object; determine whether the target object maintains the orientation direction based on the change amount of the orientation of the target object acquired from a predetermined previous time point and the change amount of the orientation direction of the target object. The controller may be configured to: determine whether the target object maintains the orientation direction; determine whether the offset between the target object and the expected driving path of the vehicle remains constant; determine a state where the offset from the left lane line or the right lane line of the lane line information on both sides of the vehicle to the target object remains constant as a first state; determine a state where the target object maintains the orientation direction as a second state; determine a state where the offset between the expected driving path of the vehicle and the target object remains constant as a third state; determine the priority order of the type states including the first state, the second state, and the third state, and predict the expected driving path of the target object based on the priority order.

[0014] According to another aspect of the present invention, a method for controlling a vehicle may include: obtaining vehicle driving information, where the vehicle driving information includes the position information, speed information, and heading direction information of the vehicle; obtaining target object driving information, where the target object driving information includes the position information, speed information, heading value information of the target object, and the surrounding road information of the vehicle; predicting an expected driving path of the vehicle based on the vehicle driving information; determining the reliability of the expected driving path of the vehicle based on a learning table, where the learning table is generated by learning based on the expected driving path of the vehicle, the global positioning system (GPS) data of the vehicle, and the internal signals of the vehicle; when the reliability of the expected driving path of the vehicle is greater than or equal to a predetermined threshold, predicting the expected driving path of the target object in real time based on the target object driving information; and operating the vehicle based on the expected driving path of the vehicle and the determined expected driving path of the target object to avoid a collision between the vehicle and the target object.

[0015] Predicting the expected driving path of the target object in real time may include: predicting the absolute speed of the target object based on the vehicle driving information and the target object driving information. Avoiding a collision between the vehicle and the target object may include: determining a first heading value of the target object based on the position of the target object using at least one of a camera, radar, or lidar; determining a second heading value of the target object based on the absolute speed; and predicting the heading direction of the target object based on the first heading value and the second heading value of the target object.

[0016] Predicting the expected driving path of the target object in real time may include: predicting an offset between the expected driving path of the target object and the expected driving path of the vehicle based on the expected driving path of the vehicle and the position information of the target object; when the offset is less than a predetermined first value, predicting a first collision point between the vehicle and the target object; and when the time difference between the vehicle and the target object reaching the first collision point is less than a predetermined second value, avoiding a collision between the vehicle and the target object.

[0017] Avoiding a collision between the vehicle and the target object may include: obtaining the surrounding road information of the vehicle, where the surrounding road information of the vehicle includes the lane line information on both sides of the vehicle; predicting an offset between the left lane line or the right lane line of the lane line information on both sides of the vehicle and the target object; when the offset is less than a predetermined first value, predicting a second collision point between the vehicle and the target object; and when the time difference between the vehicle and the target object reaching the second collision point is less than a predetermined second value, operating the vehicle to avoid a collision with the target object.

[0018] Real-time prediction of the expected travel path of a target object may include: predicting the offset between the expected travel path of the target object and the expected travel path of the vehicle based on the expected travel path of the vehicle and the position information of the target object; when the offset is less than a predetermined first value, predicting a first collision point between the vehicle and the target object; and when the time difference between the vehicle and the target object reaching the first collision point is less than a predetermined second value, avoiding a collision between the vehicle and the target object.

[0019] Avoiding a collision between the vehicle and the target object may include: obtaining the surrounding road information of the vehicle, where the surrounding road information of the vehicle includes lane line information on both sides of the vehicle; predicting the offset between the left lane line or the right lane line of the lane line information on both sides of the vehicle and the target object; when the offset is less than a predetermined first value, predicting a second collision point between the vehicle and the target object; and when the time difference between the vehicle and the target object reaching the second collision point is less than a predetermined second value, operating the vehicle to avoid a collision with the target object.

[0020] Real-time prediction of the expected travel path of a target object may include: determining a weight related to the longitudinal absolute speed of the target object based on the position of the target object; and determining the longitudinal movement direction of the target object based on the absolute speed of the target object obtained from a predetermined previous time point, the absolute speed of the target object at the current time point, and the weight.

[0021] In addition, real-time prediction of the expected travel path of a target object may include: calculating a reference value based on the lateral absolute speed of the target object and the orientation direction of the target object; and in response to determining that the reference value is greater than or equal to a predetermined third value, determining that the target object performs a lateral movement based on the absolute speed of the target object obtained from a predetermined previous time point, the absolute speed of the target object at the current time point, and the vehicle travel information.

[0022] Real-time prediction of the expected travel path of a target object may further include: determining whether the offset between the expected travel path of the target object and the expected travel path of the vehicle remains constant based on the change amount of the offset between the expected travel path of the target object and the expected travel path of the vehicle obtained from a predetermined previous time point and the change amount of the offset between the expected travel path of the target object and the expected travel path of the vehicle obtained at the current time point.

[0023] Real-time prediction of the expected travel path of a target object may further include: determining whether the offset between the target object and the left or right lane line of the vehicle remains constant based on the change amount of the offset between the target object and the left or right lane line of the vehicle obtained from a predetermined previous time point and the change amount of the offset between the target object and the left or right lane line of the vehicle obtained at the current time point. Real-time prediction of the expected travel path of a target object may include: calculating the change amount of the orientation direction of the target object; determining whether the target object maintains its orientation direction based on the change amount of the orientation of the target object obtained from a predetermined previous time point and the change amount of the orientation direction of the target object.

[0024] Further, real-time prediction of the expected travel path of a target object may include: determining whether the target object maintains its orientation direction; determining whether the offset between the target object and the expected travel path of the vehicle remains constant; determining the state where the offset from the left or right lane line of the lane line information on both sides of the vehicle to the target object remains constant as the first state; determining the state where the target object maintains its orientation direction as the second state; determining the state where the offset between the expected travel path of the vehicle and the target object remains constant as the third state; determining the priority order of the type states including the first state, the second state, and the third state, and predicting the expected travel path of the target object based on the priority order. Brief Description of the Drawings

[0025] These aspects and / or other aspects of the present invention will become apparent and easier to understand through the description of the exemplary embodiments presented in conjunction with the accompanying drawings hereinafter, in which:

[0026] Figure 1 is a schematic diagram for describing the process of predicting the expected travel path of a target object 2 located in front of a vehicle according to an exemplary embodiment;

[0027] Figure 2 is a control block diagram of a vehicle according to an exemplary embodiment;

[0028] Figure 3 is a flowchart showing the operation of determining the orientation direction of a target object located in front of a vehicle according to an exemplary embodiment;

[0029] Figure 4 is a schematic diagram showing the operation of predicting the offset between the target object and the expected travel path of the vehicle according to an exemplary embodiment;

[0030] Figure 5 is a schematic diagram showing the operation of predicting the offset between the target object and the lane lines on both sides of the vehicle according to an exemplary embodiment;

[0031] Figure 6is a schematic diagram showing an operation of determining a type of longitudinal movement of a target object according to an exemplary embodiment;

[0032] Figure 7 is a schematic diagram showing an operation of determining whether a target object makes a lateral movement according to an exemplary embodiment;

[0033] Figure 8 is a schematic diagram showing an operation of determining whether a target object maintains a facing direction according to an exemplary embodiment;

[0034] Figure 9 is a schematic diagram showing an operation of determining whether an offset between a target object and an expected driving path of a vehicle is maintained according to an exemplary embodiment;

[0035] Figure 10 is a schematic diagram showing an operation of determining whether an offset between a target object and lane lines on both sides of a vehicle is maintained according to an exemplary embodiment;

[0036] Figure 11 is a schematic diagram showing an example of an operation of determining an expected driving path of a target object by determining a priority order based on a driving state of the target object according to an exemplary embodiment;

[0037] Figure 12 is a flowchart according to an exemplary embodiment. Detailed Description

[0038] The terms used herein are for the purpose of describing particular embodiments only and are not intended to limit the present invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that when the terms "comprises" and / or "comprising" are used in this specification, it indicates the presence of the stated features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0039] It should be understood that the term "vehicle" or "vehicular" or other similar terms used herein include general motor vehicles, such as passenger cars including sport utility vehicles (SUVs), buses, trucks, various commercial vehicles, boats including various boats and ships, and aircrafts, etc., and include hybrid vehicles, electric vehicles, internal combustion engine vehicles, plug-in hybrid electric vehicles, hydrogen-powered vehicles and other alternative fuel vehicles (e.g., fuels derived from non-fossil energy sources).

[0040] While the exemplary embodiments are described as using multiple units to perform the exemplary processes, it should be understood that the exemplary processes can also be performed by one or more modules. In addition, it should be understood that the term "controller / control unit" refers to a hardware device that includes a memory and a processor and is specifically programmed to perform the processes described herein. The memory is configured to store the modules, and the processor is specifically configured to execute the modules to perform one or more of the processes described further below.

[0041] In addition, the control logic of the present invention can be implemented as a non-transitory computer-readable medium on a computer-readable medium that contains executable program instructions executed by a processor, a controller / control unit, etc. Examples of the computer-readable medium include, but are not limited to, ROM, RAM, compact disc (CD)-ROM, magnetic tape, floppy disk, flash drive, smart card, and optical data storage device. The computer-readable recording medium can also be distributed over network-connected computer systems so that the computer-readable medium is stored and executed in a distributed manner, for example, by a telematics server or a controller area network (CAN).

[0042] Unless otherwise specified or obvious from the context, the term "about" as used herein is understood to be within the normal tolerances in the art, for example, within two standard deviations of the average value. "About" can be understood to be within 10%, 9%, 8%, 7%, 6%, 5%, 4%, 3%, 2%, 1%, 0.5%, 0.1%, 0.05%, or 0.01% of the specified value. Unless the context clearly dictates otherwise, all numerical values provided herein are modified by the term "about".

[0043] Throughout the specification, the same reference numerals refer to the same elements. Not all elements of the embodiments of the present invention will be described, but descriptions of elements known in the art or elements that overlap with each other in the exemplary embodiments will be omitted. Terms used throughout the specification, such as "~ component", "~ module", "~ member", "~ block", etc., can be implemented in software and / or hardware, and multiple "~ components", "~ modules", "~ members", or "~ blocks" can be implemented in a single element, or a single "~ component", "~ module", "~ member", or "~ block" can include multiple elements.

[0044] It will also be understood that the term "connected" or its derivatives refer to both direct connection and indirect connection, and indirect connection includes connection through a wireless communication network. It will also be understood that when the terms "comprises" and / or "comprising" are used in this specification, it indicates the presence of the stated features, values, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, values, steps, operations, elements, components, and / or their groups.

[0045] Although terms such as "first", "second", "A", "B", etc. may be used to describe various components, these terms do not limit the corresponding components but are only used to distinguish one component from another. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The reference numerals used for method steps are for convenience of description only and do not limit the order of the steps. Thus, unless the context clearly indicates otherwise, the written order may be performed in a different manner.

[0046] The principles and exemplary embodiments of the present invention will be described below with reference to the accompanying drawings.

[0047] Figure 1 is a schematic diagram for describing a process of predicting an expected travel path of a target object 2 located in front of a vehicle according to an exemplary embodiment. Figure 2 is a control block diagram of a vehicle according to an exemplary embodiment. Refer to Figure 1 and Figure 2 , the vehicle 1 can use the first sensor unit 100 to obtain travel information of the vehicle 1, including position information of the vehicle 1, speed information of the vehicle 1, and orientation direction information of the vehicle 1.

[0048] The second sensor unit 300 can be configured to obtain travel information of the target object 2 and information about the surrounding road of the vehicle 1, and the travel information includes position information of the target object 2, speed information of the target object 2, and orientation value information of the target object 2. The controller 200 can be configured to predict an expected travel path (12) of the vehicle 1 based on the vehicle travel information, determine the reliability of the expected travel path based on the global positioning system (GPS) data of the vehicle 1 and the expected travel path of the vehicle 1, when the reliability of the expected travel path of the vehicle 1 is greater than or equal to a predetermined threshold, determine an expected travel path (13) of the target object 2 based on the travel information of the target object 2, and operate the drive unit 500 based on the expected travel path of the vehicle 1 and the expected travel path of the target object 2 to avoid a collision with the target object 2.

[0049] The driving unit 500 can be configured to perform functions such as changing the direction of the vehicle 1 or adjusting the speed. Specifically, the controller 200 can be configured to determine the absolute speed of the target object 2 based on the driving information of the vehicle 1 and the driving information of the target object 2. By correcting a predetermined value based on the relative speed included in the driving information of the target object 2, the driving information of the vehicle, and the position of the target object 2, the absolute speed of the target object 2 (the absolute speed of the target object 2 is different from the relative speed of the target object 2) can be determined. Based on the GPS data of the vehicle and the expected driving path of the vehicle 1, the reliability of the expected driving path of the vehicle 1 can be determined. Specifically, based on the error between the GPS data of the vehicle 1 and the expected driving path of the vehicle 1, a reliability table can be generated, and the reliability table can be inserted into the logic so that the reliability according to the corresponding signal can be obtained from the vehicle 1 at normal times.

[0050] First, a reliability learning reference signal (input) is defined, a reference signal learning part is divided, and a part according to the input signal is randomly learned. Then, the average value of the error accumulation can be updated to generate a reliability table. Specifically, the average value of the error accumulation can be learned based on measurement data, and the reliability table can be selected according to the input signal. The reliability of the expected driving path of the vehicle can be determined based on the learning table, which is generated by pre-learning based on the expected driving path of the vehicle, the GPS data of the vehicle, and the internal signal of the vehicle.

[0051] Once the reliability table is formed, the reliability can be obtained in real time based on the reliability table. The reliability of the expected driving path determined in real time can be compared with a predetermined threshold, and in response to determining that the reliability of the expected driving path of the vehicle is greater than or equal to the predetermined threshold, the expected driving path (13) of the target object 2 can be predicted in real time based on the driving information of the target object 2. Specifically, the threshold can vary according to the driving state of the target object 2. Determining the driving state of the target object 2 can include: determining the state in which the offset from the left lane line (Lh) or the right lane line (Rh) of the lane line information on both sides of the vehicle 1 to the target object 2 is kept constant as the first state, the state in which the orientation direction of the target object 2 is kept as the second state, the state in which the offset between the expected driving path of the vehicle 1 and the target object 2 is kept constant as the third state, the state in which the target object 2 stops as the fourth state, and the state in which the target object 2 travels linearly as the fifth state. The minimum value required to determine each driving state can be determined as the corresponding threshold. The offset can represent the distance to be measured.

[0052] In response to determining that the reliability value of vehicle 1 is less than a threshold, for example, when vehicle 1 experiences a significant change in the moving direction and drives irregularly, it may not be possible to correctly predict the expected driving path, and the reliability may decrease. The reliability of the expected driving path of vehicle 1 being greater than or equal to the threshold indicates that the expected driving path of vehicle 1 is predictable.

[0053] The controller 200 may be configured to predict the expected driving path (12) of vehicle 1 in real time, predict the expected driving path (13) of the target object 2, predict a collision between vehicle 1 and the target object 2 based on the expected driving path of vehicle 1 and the expected driving path of the target object 2, and operate the driving unit 500 to avoid the collision. The controller 200 may include a memory (not shown) and a processor (not shown), the memory being configured to store data related to an algorithm for executing the operations of the components of vehicle 1 or a program representing the algorithm, and the processor using the data stored in the memory to perform the above operations. At this time, the memory and the processor may be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0054] At least one component may be added or omitted to correspond to Figure 1 and Figure 2 the performance of the components of the system shown in. Additionally, the relative positions of the components may be changed to correspond to the performance or structure of the system. Figure 1 and Figure 2 Some of the components shown in may refer to software components and / or hardware components, such as field programmable gate arrays (FPGAs) and application specific integrated circuits (ASICs).

[0055] Figure 3 is a flowchart showing an operation of determining the orientation direction of the target object 2 in front of the vehicle according to an exemplary embodiment. The second sensor may include a camera, a radar, and a lidar, and the controller 200 may be configured to determine a first orientation value (d1) of the target object 2 based on the position of the target object 2 using at least one second sensor; determine a second orientation value (d2) of the target object 2 based on the absolute speed of the target object 2; compare the first orientation value of the target object 2 and the second orientation value of the target object 2 (d3); and predict the orientation direction of the target object 2 based on the first orientation value and the second orientation value.

[0056] Specifically, the controller 200 may be configured to select at least one of the radar, lidar, and camera of the second sensor unit 300 based on the position of the target object 2, and select a first orientation value (d1). The controller may be configured to predict the absolute speed of the target object 2 and determine a second orientation value (d2) based on the predicted absolute speed. The second orientation value may be determined based on the ratio of the lateral absolute speed of the target object 2 to the longitudinal absolute speed of the target object 2. When the target object 2 may be in front of the vehicle 1, the camera may be preferentially selected, and in other cases, the lateral radar may be selected to determine the first orientation value. Specifically, the sensed value of the sensor changes according to the position of the target object 2.

[0057] Thereafter, the controller 200 may be configured to compare the first orientation value with the second orientation value (d3) to select a strategy (d4) for obtaining the orientation direction. Specifically, in response to determining that the difference between the first orientation value and the second orientation value greatly exceeds a specific threshold, the controller 200 may be configured to determine that the orientation direction is unpredictable, and in response to determining that the difference between the first orientation value and the second orientation value exceeds the specific threshold to an appropriate extent, mix the first orientation value and the second orientation value in a predetermined ratio, and select a strategy (d4) for obtaining the orientation direction. For example, when the camera is selected as the sensor for obtaining the orientation value, due to the image recognition characteristics, the camera is more suitable for recognizing inclined shapes than the radar. Therefore, for the target object 2 in front of the vehicle, a higher specific threshold may be set. As the difference between the first orientation value and the second orientation value increases, the second orientation value may be preferentially determined. In response to determining that the difference between the first orientation value and the second orientation value is less than the threshold, the first orientation value may be determined as the orientation direction.

[0058] Figure 4 It is a schematic diagram showing an operation of predicting the offset between the target object 2 and the expected travel path of the vehicle 1 according to an exemplary embodiment. The controller 200 may be configured to calculate the offset between the target object 2 and the expected travel path of the vehicle 1 based on the expected travel path of the vehicle 1 and the position information of the target object 2. When the offset is less than a first predetermined value, the point on the expected travel path closest to the target object 2 is determined as the collision point, and in response to determining that the time difference between the vehicle 1 and the target object 2 reaching the collision point is less than a second predetermined value, the controller 200 may be configured to operate the drive unit 500 to avoid colliding with the target object 2.

[0059] Reference Figure 4, the offset between the target object 2 and the expected driving path 26 of the vehicle 1 can be predicted based on the expected driving path 26 of the vehicle 1 and the position of the target object 2. Assuming a line is drawn in the direction pointed by the orientation direction of the vehicle 1, the difference between the distance 21 from this line to the target object 2 and the distance 22 from this line to the expected driving path 26 of the vehicle 1 represents the offset 25 between the target object 2 and the expected driving path 26 of the vehicle 1. In this case, the distance 22 from this line to the expected driving path 26 of the vehicle 1 can be expressed as: the product of the angle 24 formed by the expected driving path 26 of the vehicle 1 and this line and the distance between the vehicle and the target object.

[0060] When the offset between the target object 2 and the expected driving path 26 of the vehicle 1 is less than a predetermined first value, it can be predicted that the vehicle 1 and the target object 2 will collide. The collision point refers to the point on the expected driving path 26 of the vehicle 1 where a collision with the target object 2 is predicted. The difference between the time taken for the vehicle 1 to reach the collision point and the time taken for the target object 2 to reach the collision point can be calculated, and in response to determining that this difference is less than a predetermined value, it is determined that the vehicle 1 and the target object 2 will collide, and the controller 200 can be configured to operate the drive unit 500 of the vehicle 1.

[0061] Specifically, the distance 22 between the line drawn in the direction pointed by the orientation direction and the expected driving path 26 of the vehicle 1 can be calculated as follows: obtaining the angle formed between the line drawn in the direction pointed by the orientation direction of the vehicle and the point expected to be the collision point of the expected driving path 26 of the vehicle 1 relative to the vehicle 1, and multiplying this angle by the distance from the vehicle 1 to the target object 2. The distance 21 between the line drawn in the direction the vehicle is facing and the target object 2 can be determined based on the distance between the vehicle 1 and the target object 2 and the angle 23 formed between the line drawn in the direction pointed by the orientation direction and the target object 2.

[0062] The distance 21 between the line and the target object 2 can be obtained by multiplying the distance between the vehicle 1 and the target object 2 by the sine value. In this case, the angle input into the sine value refers to the angle 23 formed between the line drawn in the direction pointed by the orientation direction of the vehicle 1 and the target object 2 relative to the vehicle 1. Specifically, the angle 24 from the line to the point expected to be the collision point can be half of the angle 27 formed between the line Rc1 passing through the target object 2 and the line Rc2 passing through the vehicle 1 drawn in the direction pointed by the orientation direction of the vehicle 1. As described below, when the value of the offset 25 remains constant, it can be determined that the offset between the expected driving path of the vehicle 1 and the target object 2 remains constant. Specifically, the distance between the target object 2 and the expected driving path of the vehicle 1 can be obtained using a variable filter that receives the signal of the vehicle 1 as an input.

[0063] Figure 5 This is a schematic diagram showing an operation of predicting an offset between a target object and a lane line according to an exemplary embodiment. Information about the surrounding road of the vehicle 1 obtained by the second sensor unit 300 may include information about the lane lines on both sides of the vehicle 1, and the controller 200 may be configured to calculate an offset from the left lane line Lh or the right lane line Rh included in the information about the lane lines on both sides of the vehicle 1 to the target object 2. In response to determining that the offset is less than a predetermined first value, the controller 200 may be configured to determine the point on the left lane line Lh or the right lane line Rh closest to the target object 2 as the second collision point, and in response to determining that the time difference between the vehicle 1 and the target object 2 reaching the second collision point is less than a second predetermined value, operate the driving unit 500 to avoid a collision with the target object 2.

[0064] Specifically, information about the lane lines on both sides of the vehicle 1 may be obtained from the second sensor unit 300, and an offset from the left lane line Lh or the right lane line Rh on both sides of the vehicle 1 to the target object 2 may be calculated. For example, when the target object 2 is located on the right side of the right lane line of the vehicle 1, an offset 34 between the right lane line and the target object 2 may be calculated to obtain an offset between a specific point on the right lane line and the target object 2. When the target object 2 is located on the left side of the left lane line of the vehicle 1, an offset between the left lane line and the target object 2 may be obtained. When the offset is less than a predetermined first value, the point on the left lane line Lh or the right lane line Rh closest to the target object 2 may be determined as the second collision point 31 or 32. Specifically, in response to determining that the time difference taken for the vehicle 1 and the target object 2 to reach the second collision point 31 or 32 is less than a second predetermined value, control may be executed to avoid a collision with the target object 2.

[0065] Figure 6 This is a schematic diagram showing an operation of determining the type of longitudinal movement of the target object 2 according to an exemplary embodiment. The controller 200 may be configured to determine a weight related to the longitudinal absolute speed of the target object 2 based on the position of the target object 2, and determine the longitudinal movement direction of the target object 2 based on the absolute speed of the target object 2 obtained from the previous time point, the absolute speed of the target object 2 at the current time point, and the weight.

[0066] Specifically, with reference to Figure 6, the controller 200 may be configured to determine a weight related to the longitudinal absolute speed of the target object 2 based on the position of the target object 2. For example, as the angle between the target object 2 and the vehicle 1 increases, the cognitive ability of the sensor may decrease. Specifically, when determining the range of the forward movement determination area, a higher weight may be assigned for accurate determination. In response to an increase in the angle between the target object 2 and the vehicle 1, the weight may be set higher to increase the threshold, and since the threshold increases, it can be determined that the target object 2 moves forward only when the longitudinal absolute speed of the target object 2 is measured to be high.

[0067] Specifically, the threshold corresponds to a value that is based on the weight and is used as a criterion for determining whether the target object corresponds to forward movement or reverse movement. Since the reverse movement determination area 41 is generally formed in a large range, movement in the direction opposite to the vehicle 1 can be determined as reverse movement, regardless of the angle formed between the vehicle 1 and the target object 2. In this case, hysteresis (the concept of age) can be used to determine forward movement or reverse movement. For example, assume that at a specific time point, the target object 2 traveling in the direction opposite to the vehicle 1 is measured to be traveling at a relative speed of -100, and after a certain period of time, the target object 2 makes a U-turn and travels at an absolute speed of +10, while the vehicle 1 travels at an absolute speed of +120. Then, the absolute speed of the target object 2 calculated by the vehicle 1 is -110. Although the vehicle 1 and the target object 2 are currently traveling in the same direction (forward movement), it can be determined that the target object 2 is traveling in the opposite direction (reverse movement) only when determined numerically.

[0068] Therefore, the concept of hysteresis can be used to eliminate this limitation. Hysteresis (i.e., the hysteresis phenomenon) represents predicting the state at a specific time point by referring to the phenomenon before a specific time point. In other words, based on the information obtained from a predetermined previous time point and the information at the current time point, it can be observed that the speed of the target object 2 changes over a certain period of time, and it is found that the speed has decreased and the measured speed is gradually changing. Therefore, the controller 200 may be configured to predict the direction change of the target object 2.

[0069] The longitudinal absolute speed of the target object is set as the vertical axis 45, the angle between the target object 2 and the vehicle 1 is set as the horizontal axis 44, the angle formed between the target object 2 and the vehicle 1 according to the position of the target object 2 is obtained, the longitudinal absolute speed of the target object 2 is obtained, and it can be determined whether the target object 2 corresponds to the forward movement determination area 42 or the reverse movement determination area 41 based on the information obtained from a predetermined previous time point, the absolute speed of the target object 2 at the current time point, and the weight.

[0070] Figure 7It is a schematic diagram showing an operation of determining whether a target object performs a lateral movement according to an exemplary embodiment. The controller 200 may be configured to calculate a reference value based on the lateral absolute velocity of the target object and the orientation direction of the target object, and in response to determining that the reference value is greater than or equal to a third predetermined value, the controller 200 may be configured to determine that the target object 2 performs a lateral movement based on the absolute velocity of the target object acquired from a predetermined previous time point, the absolute velocity of the target object at the current time point, and the information acquired from the first sensor unit 100.

[0071] Reference Figure 7 , the reference value can be determined based on the lateral absolute velocity and the orientation direction of the target object. In response to determining that the reference value is greater than or equal to the third predetermined value, it can be determined that the target object 52 performs a lateral movement. Specifically, when the reference value is less than the third predetermined value, the lateral movement may be inaccurately determined. When the reference value is greater than or equal to the third predetermined value, the concept of hysteresis can be used to determine the execution of the lateral movement. Whether to perform the lateral movement can be determined based on the absolute velocity of the target object 52 acquired from a predetermined previous time point, the absolute velocity of the target object 52 at the current time point, and the driving information of the vehicle 1.

[0072] For example, when the vehicle turns, the angle between the target object and the vehicle changes greatly over time, so it is meaningless to determine whether the target object performs a lateral movement. When the vehicle 1 turns with a large radius from a predetermined previous time point, the angle formed between the vehicle and the target object changes continuously and the speed also changes, so it cannot be determined that the target object is performing a lateral movement. When the speed is greater than the value obtained by multiplying the longitudinal absolute velocity by a specific ratio, the vehicle 1 is not moving fast, and the path of the vehicle 1 is predicted to be a straight path, it is determined that the lateral movement is performed. Specifically, the reference value can be compared with a threshold value for a final determination. Figure 7 The target object 51 is also shown, and the lateral movement of the target object 51 is determined, even with low accuracy. The above determination can be performed by calculating a reference value for inaccurately determining the lateral movement based on the predicted longitudinal / lateral absolute velocity and applying this reference value to the concept of hysteresis.

[0073] Figure 8 It is a schematic diagram showing an operation of determining whether a target object maintains its orientation direction according to an exemplary embodiment. The controller 200 may be configured to calculate the change amount of the orientation direction of the target object, calculate the change amount of the orientation of the target object acquired from a previously determined time point, and determine whether the target object 2 maintains its orientation direction based on the change amount of the orientation direction of the target object and the change amount of the orientation of the target object acquired from a predetermined previous time point.

[0074] Specifically, reference Figure 8, the first target object 63 traveling in the same direction as the vehicle 1 stops maintaining its orientation direction. The controller 200 may be configured to calculate the amount of change in the orientation of the first target object 63 and the amount of change in the orientation direction of the first target object 63 obtained from a predetermined previous time point, and determine that the current orientation direction of the first target object 63 is not maintained based on whether the orientation direction of the first target object 63 has been changing since the previous time point and how much the orientation direction of the first target object 63 has changed. In the case of the second target object 62, Figure 8 It is shown that the second target object 62 changes its orientation direction to an adjacent lane when traveling from behind the vehicle 1. In this regard, the controller 200 of the vehicle 1 may be configured to calculate that the orientation direction of the second target object 62 has been changing since a predetermined previous time point and is still changing even at the current time point, thereby determining that the second target object 2 is changing its orientation direction.

[0075] The third target object 61 travels in the opposite direction to the vehicle 1, maintains a constant orientation direction from a predetermined previous time point to the current time point, and corresponds to an example where the vehicle 1 determines that the third target object 61 maintains its orientation direction. The fourth target object 64 corresponds to an example where the controller 200 calculates that the fourth target object 64 travels in the same direction as the vehicle 1 and has been changing its orientation direction since a predetermined previous time point, observes that the orientation direction of the fourth target object 64 is currently changing, and determines that the orientation direction is not maintained. For the case of the fifth target object 65, since the fifth target object 65 is turning while the vehicle 1 is traveling, it can be determined that the orientation direction of the fifth target object 65 continuously changes from a predetermined previous time point to the current time point and thus maintains its orientation direction. In this case, it can be determined that the fifth target object 65 is turning.

[0076] When the vehicle turns, the angle between the target object and the vehicle changes greatly over time. Therefore, due to the limited performance of the camera and radar, it may be difficult to ensure the reliability of calculating the amount of change in orientation. The calculation method of the reference value for determining the maintenance of the orientation direction has the following requirements: the amount of change in the orientation direction is less than or equal to a specific threshold, the vehicle 1 does not move suddenly, and the overall expected travel path of the vehicle 1 is a straight path. The calculation method of the reference value for determining whether the target object is turning has the following requirements: the amount of change in the orientation of the target object is greater than or equal to a specific threshold, the vehicle 1 does not move suddenly, and the path of the vehicle 1 is a straight path as a whole.

[0077] Figure 9 is a schematic diagram showing the operation of determining whether the offset between the target object 2 and the expected travel path of the vehicle 1 is maintained. Refer to Figure 9, it is possible to determine the offsets between the vehicles 71, 72, and 75 moving forward in the same direction as the vehicle 1 and the expected travel path of the vehicle 1. In response to determining that the offsets between the vehicles 71, 72, and 75 moving forward in the same direction as the vehicle 1 and the expected travel path of the vehicle 1 are constant, it can be determined that the offsets from the expected travel path of the vehicle 1 remain constant. It is possible to determine the offsets between the vehicles 73, 74, and 76 moving in the opposite direction to the vehicle 1 and the expected travel path of the vehicle 1. When the offsets between the vehicles 73, 74, and 76 moving in the opposite direction to the vehicle 1 and the expected travel path of the vehicle 1 are constant, it can be determined that the offsets from the expected travel path of the vehicle 1 remain constant.

[0078] When determining whether the offset remains constant, the concept of hysteresis can be used. In other words, when the distances between the vehicles 71, 72, 73, 74, 75, and 76 and the expected travel path of the vehicle 1 obtained from a predetermined previous time point are constant and the error is less than a specific value, it can be determined that the offset remains constant.

[0079] Specifically, the method for determining whether the offset remains constant has the following requirements: the change amount of the offset from the expected travel path of the vehicle 1 is less than or equal to a specific threshold, the identified target object 2 is within a specific range (when the position of the target object 2 is too far, the prediction accuracy may be low, and this determination may be meaningless for the system), and it is expected that the expected travel path of the vehicle 1 will not turn significantly. When the vehicle 1 is turning, the angle between the target object 2 and the vehicle 1 changes greatly over time. Therefore, due to the limited performance of the camera and radar, it is not easy to ensure the calculation reliability of the change amount of the offset from the expected travel path of the vehicle 1.

[0080] Figure 10 is a schematic diagram showing an operation of determining whether the offset between the target object 2 and the lane lines on both sides of the vehicle 1 remains constant. Refer to Figure 10 , obtain the position information of the vehicles 81 and 83 traveling in the same direction as the vehicle 1, and it is possible to determine whether the left and right lane lines of the vehicle 1 are parallel to each other (for example, the similarity of the cubic coefficients of the lane lines identified on both sides of the vehicle 1 can be compared). When the conditions for determining the parallel state are met, such as the change amount of curvature (third-order term), curvature (second-order term), and the slope of the starting position of the lane line (first-order term), the method of adding the lane width to the current position can be used to virtually generate a lane (for example, the prediction of the lane width is determined based on the offset from the starting position between the left lane line Lh or the right lane line Rh and the vehicle 1).

[0081] Based on the change amount of the offset between the left or right lane line of vehicle 1 and the target object 2 obtained from a predetermined previous time point, and the change amount of the offset between the left or right lane line of vehicle 1 and the target object 2 at the current time point, it can be determined whether the offset between the target object 2 and the expected driving path of vehicle 1 remains constant.

[0082] The lane where the target object 2 is located can be estimated. The method for determining whether the lane lines on both sides of vehicle 1 and the target object 2 maintain an offset has the following requirements: the corrected offset values between the target object 2 and the left and right lane lines are less than or equal to a specific threshold, the change amount of the offset between the left lane line Lh or the right lane line Rh of vehicle 1 and the target object 2 is equal to or greater than a specific threshold, and the lane width is greater than or equal to a specific proportional number of the vehicle width of the target object. Similar to the above, a hysteresis method can be used to provide a calculation method. As a result, it can be determined whether the offset between the lane lines on both sides of vehicle 1 and the target object 2 is maintained.

[0083] Figure 11 It is a schematic diagram showing an example of an operation for determining the expected driving path of a target object by setting a priority order for determining the driving state of the target object. Refer to Figure 11 , assuming that the information about the road around the vehicle includes the information about the lane lines on both sides of vehicle 1, the controller 200 can be configured to predict the offset between the target object and the expected driving path of the vehicle based on the expected driving path of the vehicle and the position information of the target object, and determine whether the offset between the target object and the expected driving path of the vehicle remains constant based on the change amount of the offset between the target object and the expected driving path of the vehicle obtained from a predetermined previous time point and the change amount of the offset between the target object and the expected driving path of the vehicle at the current time point.

[0084] In addition, the controller 200 may be configured to calculate a change amount of the orientation direction of the target object 2, determine whether the target object 2 maintains its orientation direction based on the change amount of the orientation direction of the target object 2 and the change amount of the orientation of the target object 2 obtained since a predetermined previous time point, determine a state where the offset from the left lane line (Lh) or the right lane line (Rh) of the lane line information on both sides of the vehicle 1 to the target object 2 remains constant as the first state, determine a state where the target object 2 maintains its orientation direction as the second state, determine a state where the offset between the expected travel path of the vehicle 1 and the target object 2 remains constant as the third state, determine a state where the target object 2 stops as the fourth state, determine a state where the target object 2 moves linearly as the fifth state, set a priority order for the first state, the second state, the third state, the fourth state, and the fifth state, and predict the expected travel path of the target object 2 based on the priority order. The type state is a state including the first state, the second state, and the third state, and the type state may include all of the first state, the second state, the third state, the fourth state, and the fifth state, and may refer to a specific driving state, such as a state where the offset between the target object and the vehicle remains constant.

[0085] Reference Figure 11 , first, it may be determined whether the target object 2 is in a stationary state (91). In response to determining that the target object 2 is in a stationary state (Yes in step 91), the reliability of the expected travel path of the vehicle 1 may be compared with a predetermined threshold (here, the threshold may be different for each state of the target object 2), and in response to determining that the reliability of the expected travel path of the vehicle 1 is greater than or equal to the predetermined threshold, the expected travel path of the target object 2 may be determined (96). When it is determined that the target object 2 is not in a stationary state (No in step 91), it may be determined whether the target object 2 is in a lane line holding state (92), and when it is determined that the target object 2 is in a lane line holding state (Yes in step 92), the reliability of the expected travel path of the vehicle 1 may be compared with a predetermined threshold.

[0086] In response to determining that the reliability of the expected travel path of the vehicle 1 is greater than or equal to the predetermined threshold, the expected travel path of the target object 2 may be determined (96). In response to determining that the target object 2 is not in a lane line holding state (No in step 92), it may be determined whether the target object 2 maintains its orientation direction (93). When the target object 2 maintains its orientation direction (93) and the reliability of the expected travel path of the vehicle 1 is greater than the predetermined threshold, the expected travel path of the target object 2 may be determined (96), and when the orientation direction of the target object 2 is not maintained, it may be determined whether the offset between the expected travel path of the vehicle 1 and the target object 2 remains constant.

[0087] In the same manner as described above, it is possible to determine whether the offset between the predicted travel path of the vehicle 1 and the target object 2 remains constant (94). In response to determining that the offset between the predicted travel path of the vehicle 1 and the target object 2 remains constant (the "yes" of 94), the reliability of the predicted travel path of the vehicle 1 can be compared with a predetermined threshold, and in response to determining that the reliability of the predicted travel path of the vehicle 1 is greater than or equal to the predetermined threshold, the predicted travel path of the target object can be determined. Additionally, in response to determining that the offset between the predicted travel path of the vehicle 1 and the target object 2 does not remain constant (the "no" of 94), the predicted travel path of the target object 2 can be determined based on the predicted absolute speed of the vehicle 1 (95). When the predicted travel path of the target object 2 is determined based on the predicted absolute speed of the vehicle 1, the reliability of the predicted travel path of the vehicle 1 is not compared with the threshold.

[0088] Figure 12 is a flowchart according to an exemplary embodiment. Refer to Figure 12 , the travel information of the vehicle 1 and the travel information of the target object 2 can be obtained (S-1), the predicted travel path of the vehicle 1 can be predicted based on the GPS data of the vehicle 1 and the travel information of the vehicle 1 (S-2), and the reliability of the predicted travel path of the vehicle 1 can be determined (S-3). As described above, the reliability can be determined based on the GPS data of the vehicle and the predicted travel path of the vehicle. When the reliability is less than the predetermined threshold, the predicted travel path of the vehicle 1 can be predicted again, and when the reliability is greater than or equal to the predetermined value, a priority order can be set for determining the travel state of the target object 2 (S-4). Thereafter, based on the priority order, the predicted travel path of the target object 2 can be predicted (S-5), and the drive unit 500 can be operated to avoid a predicted collision between the vehicle 1 and the target object 2 (S-6).

[0089] Meanwhile, the disclosed exemplary embodiment can be implemented in the form of a recording medium storing instructions executable by a computer. These instructions can be stored in the form of program code, and when executed by a processor, these instructions can generate program modules to execute the respective steps of the disclosed exemplary embodiment. The recording medium can be implemented as a non-transitory computer-readable recording medium. Non-transitory computer-readable recording media include all types of recording media storing instructions that can be decoded by a computer, such as read-only memory (ROM), random access memory (RAM), magnetic tape, magnetic disk, flash memory, optical data storage devices, and the like.

[0090] It is obvious from the above that the vehicle and its control method can predict a collision by predicting the predicted travel path of the vehicle and the predicted travel path of the target object, and avoid the predicted collision.

[0091] Although the exemplary forms of the present invention have been described for purposes of illustration, those skilled in the art should understand that various modifications, additions, and deletions can be made without departing from the scope and spirit of the present invention. Therefore, the exemplary embodiments of the present invention are not described for restrictive purposes.

Claims

1. A vehicle, comprising: A first sensor unit configured to acquire vehicle driving information, the vehicle driving information including vehicle position information, speed information, and orientation direction information; A second sensor unit configured to acquire target object driving information, the target object driving information including target object position information, speed information, orientation value information, and surrounding road information of the vehicle; A controller configured to: Predict an expected driving path of the vehicle based on the vehicle driving information; Determine the reliability of the expected driving path of the vehicle based on a learning table, the learning table being generated by learning based on the expected driving path of the vehicle, global positioning system data of the vehicle, and internal signals of the vehicle; When the reliability of the expected driving path of the vehicle is greater than or equal to a predetermined threshold, predict an expected driving path of the target object in real time based on the target object driving information; Operate the vehicle based on the expected driving path of the vehicle and the determined expected driving path of the target object to avoid a collision between the vehicle and the target object.

2. The vehicle according to claim 1, wherein, The controller is configured to predict the absolute speed of the target object based on the vehicle driving information and the target object driving information.

3. The vehicle according to claim 2, wherein, The second sensor unit includes a camera, a radar, and a lidar, and the controller is configured to: Determine a first orientation value of the target object based on the position of the target object, using at least one of the camera, radar, or lidar included in the second sensor unit; Determine a second orientation value of the target object based on the absolute speed; Predict the orientation direction of the target object based on the first orientation value of the target object and the second orientation value of the target object.

4. The vehicle according to claim 1, wherein, The controller is configured to: Predict an offset between the expected driving path of the target object and the expected driving path of the vehicle based on the expected driving path of the vehicle and the position information of the target object; In response to determining that the offset is less than a predetermined first value, predict a first collision point between the vehicle and the target object; In response to determining that the time difference for the vehicle and the target object to reach the first collision point is less than a predetermined second value, operate the vehicle to avoid a collision with the target object.

5. The vehicle according to claim 1, wherein, The surrounding road information of the vehicle includes lane line information on both sides of the vehicle, and the controller is configured to: Predict an offset between the left lane line or the right lane line of the lane line information on both sides of the vehicle and the target object; In response to determining that the offset is less than a predetermined first value, predict a second collision point between the vehicle and the target object; In response to determining that the time difference for the vehicle and the target object to reach the second collision point is less than a predetermined second value, operate the drive unit to avoid a collision with the target object.

6. The vehicle according to claim 2, wherein, The controller is configured to: Determine a weight related to the longitudinal absolute speed of the target object according to the position of the target object; Determine the longitudinal movement direction of the target object based on the absolute speed of the target object acquired from a predetermined previous time point, the absolute speed of the target object at the current time point, and the weight.

7. The vehicle according to claim 2, wherein, The controller is configured to: Calculate a reference value based on the lateral absolute speed of the target object and the orientation direction of the target object, When the reference value is greater than or equal to a predetermined third value, it is determined that the target object performs a lateral movement based on the absolute speed of the target object acquired from a predetermined previous time point, the absolute speed of the target object at the current time point, and the vehicle driving information.

8. The vehicle according to claim 4, wherein, The controller is configured to: determine whether the offset between the target object and the expected driving path of the vehicle remains constant based on the change amount of the offset between the target object and the expected driving path of the vehicle acquired from a predetermined previous time point and the change amount of the offset between the target object and the expected driving path of the vehicle acquired at the current time point.

9. The vehicle according to claim 5, wherein, The controller is configured to: determine whether the offset between the target object and the expected driving path of the vehicle remains constant based on the change amount of the offset between the target object and the left or right lane line of the vehicle acquired from a predetermined previous time point and the change amount of the offset between the target object and the left or right lane line of the vehicle acquired at the current time point.

10. The vehicle according to claim 3, wherein, The controller is configured to: calculate the change amount of the orientation direction of the target object; determine whether the target object maintains its orientation direction based on the change amount of the orientation of the target object acquired from a predetermined previous time point and the calculated change amount of the orientation direction of the target object.

11. The vehicle according to claim 8, wherein, The controller is configured to: determine whether the target object maintains its orientation direction; determine whether the offset between the target object and the expected driving path of the vehicle remains constant; determine the state where the offset from the left or right lane line of the lane line information on both sides of the vehicle to the target object remains constant as the first state; determine the state where the target object maintains its orientation direction as the second state; determine the state where the offset between the expected driving path of the vehicle and the target object remains constant as the third state; determine the priority order of the type states including the first state, the second state, and the third state, and predict the expected driving path of the target object based on the priority order.

12. A method for controlling a vehicle, comprising: acquiring, by a controller, vehicle driving information, where the vehicle driving information includes vehicle position information, speed information, and orientation direction information; acquiring, by the controller, target object driving information, where the target object driving information includes target object position information, speed information, orientation value information, and surrounding road information of the vehicle; predicting, by the controller, the expected driving path of the vehicle based on the vehicle driving information; determining, by the controller, the reliability of the expected driving path of the vehicle based on a learning table, where the learning table is generated by learning based on the expected driving path of the vehicle, the global positioning system data of the vehicle, and the internal signals of the vehicle; when the reliability of the expected driving path of the vehicle is greater than or equal to a predetermined threshold, predicting, by the controller, the expected driving path of the target object in real time based on the target object driving information; operating, by the controller, the vehicle based on the expected driving path of the vehicle and the determined expected driving path of the target object to avoid a collision between the vehicle and the target object.

13. The method according to claim 12, wherein, Predicting the expected driving path of the target object in real time includes: predicting the absolute speed of the target object based on the vehicle driving information and the target object driving information.

14. The method according to claim 13, wherein avoiding a collision between the vehicle and the target object includes: The controller determines a first orientation value of the target object based on the position of the target object, using at least one of a camera, a radar, or a lidar. The controller determines a second orientation value of the target object based on the absolute speed. The controller predicts the orientation direction of the target object based on the first orientation value and the second orientation value of the target object.

15. The method according to claim 12, wherein, Predicting the expected travel path of the target object in real time includes: The controller predicts an offset between the expected travel path of the vehicle and the expected travel path of the target object based on the expected travel path of the vehicle and the position information of the target object. When the offset is less than a predetermined first value, the controller predicts a first collision point between the vehicle and the target object. When the time difference between the vehicle and the target object reaching the first collision point is less than a predetermined second value, the controller operates the vehicle to avoid a collision with the target object.

16. The method according to claim 12, wherein, Avoiding a collision between the vehicle and the target object includes: The controller obtains the surrounding road information of the vehicle, and the surrounding road information of the vehicle includes lane line information on both sides of the vehicle. The controller predicts an offset between the left lane line or the right lane line of the lane line information on both sides of the vehicle and the target object. When the offset is less than a predetermined first value, the controller predicts a second collision point between the vehicle and the target object. When the time difference between the vehicle and the target object reaching the second collision point is less than a predetermined second value, the controller operates the vehicle to avoid a collision with the target object.

17. The method according to claim 13, wherein, Predicting the expected travel path of the target object in real time includes: The controller determines a weight related to the longitudinal absolute speed of the target object according to the position of the target object. The controller determines the longitudinal movement direction of the target object based on the absolute speed of the target object obtained from a predetermined previous time point, the absolute speed of the target object at the current time point, and the weight.

18. The method according to claim 13, wherein, Predicting the expected travel path of the target object in real time includes: The controller calculates a reference value based on the lateral absolute speed of the target object and the orientation direction of the target object. In response to determining that the reference value is greater than or equal to a predetermined third value, the controller determines that the target object performs a lateral movement based on the absolute speed of the target object obtained from a predetermined previous time point, the absolute speed of the target object at the current time point, and the vehicle travel information.

19. The method according to claim 15, wherein, Predicting the expected travel path of the target object in real time includes: determining whether the offset between the expected travel path of the target object and the expected travel path of the vehicle remains constant based on the change amount of the offset between the expected travel path of the target object and the expected travel path of the vehicle obtained from a predetermined previous time point and the change amount of the offset between the expected travel path of the target object and the expected travel path of the vehicle obtained at the current time point.

20. The method according to claim 16, wherein Predicting the expected travel path of the target object in real time includes: determining whether the offset between the expected travel path of the target object and the expected travel path of the vehicle remains constant based on the change amount of the offset between the target object and the left lane line or the right lane line of the vehicle obtained from a predetermined previous time point and the change amount of the offset between the target object and the left lane line or the right lane line of the vehicle obtained at the current time point.

21. The method according to claim 14, wherein Real-time prediction of the expected driving path of a target object includes: The controller calculates the change amount of the orientation direction of the target object; The controller determines whether the target object maintains its orientation direction based on the change amount of the orientation of the target object obtained since a predetermined previous time point and the calculated change amount of the orientation direction of the target object.

22. The method according to claim 18, wherein Real-time prediction of the expected driving path of a target object includes: The controller determines whether the target object maintains its orientation direction; The controller determines whether the offset between the target object and the expected driving path of the vehicle remains constant; The controller determines the state where the offset from the left lane line or the right lane line of the lane line information on both sides of the vehicle to the target object remains constant as the first state; The controller determines the state where the target object maintains its orientation direction as the second state; The controller determines the state where the offset between the expected driving path of the vehicle and the target object remains constant as the third state; The controller determines the priority order of the type states including the first state, the second state, and the third state, and predicts the expected driving path of the target object based on the priority order.

Images