Autonomous traveling vehicle and control method thereof

The characteristics and impact points of the target vehicle are determined through sensor information, and the appropriate avoidance mode is selected to control autonomous driving vehicles, which solves the braking control problems caused by long target vehicles and improves driving stability and reliability.

CN119058669APending Publication Date: 2024-12-03HYUNDAI MOTOR CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311608803.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-06-02
Filing Date
2023-11-28
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

When existing autonomous driving systems face long target vehicles, braking control is prone to be too sensitive or error-free, and braking volume is insufficient when there is a lack of steering avoidance areas, resulting in a high collision risk.

Method used

Receiving information through multiple sensors, determining whether the length and width of the target vehicle meet the reference conditions, calculating the impact point type and collision index, and selecting an appropriate avoidance mode (first avoidance mode or second avoidance mode) to control the vehicle's driving , the first avoidance mode does not use additional deceleration, and the second avoidance mode uses an extended function to ensure additional deceleration.

Benefits of technology

Improve the collision prediction and avoidance ability of autonomous vehicles when facing long target vehicles, enhance driving stability and reliability, and reduce uncontrolled braking and sensitive control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119058669A_ABST
    Figure CN119058669A_ABST
Patent Text Reader

Abstract

The invention relates to a device for controlling the autonomous driving of a host vehicle. The apparatus may include a processor; and a memory storing instructions that, when executed by the processor, may cause the apparatus to: receive sensor information from at least one of a plurality of sensors mounted on the host vehicle; determining whether another vehicle traveling within a threshold distance from the host vehicle satisfies a target condition based on the sensor information; setting the other vehicle as a target vehicle based on the condition that the other vehicle satisfies the target condition; determining an avoidance condition between the target vehicle and the vehicle; and controlling autonomous driving of the host vehicle to operate in the first avoidance mode or the second avoidance mode based on the avoidance condition.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to an autonomous driving vehicle and a control method thereof. Background Art

[0002] The driving safety system can brake the host vehicle based on the rear center point of a target vehicle traveling in front of or around the host vehicle.

[0003] In the case where the target vehicle is long, that is, the target length is long, if braking is performed based on the rear of the long target, there is a high possibility that the braking control is too sensitive or the control is erroneous.

[0004] Additionally or alternatively, in the driving safety system, if there is no avoidance area for turning around the driving path of the host vehicle, when braking is performed at the control time, the braking amount may be insufficient, so the possibility of collision with the target vehicle is high. Summary of the invention

[0005] According to the present disclosure, a device for controlling the autonomous driving of a vehicle may include: a processor; and a memory storing instructions, wherein the instructions, when executed by the processor, may enable the device to: receive sensor information from at least one of a plurality of sensors installed on the vehicle; determine, based on the sensor information, whether other vehicles traveling within a threshold distance from the vehicle meet a target condition; set the other vehicles as target vehicles based on the other vehicles meeting the target condition; determine an avoidance condition between the target vehicle and the vehicle; and, based on the avoidance condition, control the autonomous driving of the vehicle to operate in a first avoidance mode or a second avoidance mode.

[0006] The device, wherein the instructions, when executed by the processor, can cause the device to: determine that the target condition is satisfied based on the length of the other vehicle being longer than a reference length and based on the width of the other vehicle being wider than a reference width. The device, wherein the instructions, when executed by the processor, can cause the device to: calculate a collision point between the host vehicle and the target vehicle based on the satisfaction of the target condition, and determine the collision type as the first collision type or the second collision type based on the calculated collision point.

[0007] The device, wherein the instructions, when executed by the processor, can cause the device to: determine the collision type as the first collision type based on the calculated collision point on the X-axis being within the side collision range of the target vehicle. The device, wherein the instructions, when executed by the processor, can cause the device to: determine the collision type as the second collision type based on the calculated collision point on the Y-axis being within the side collision range of the target vehicle.

[0008] The device, wherein the instructions, when executed by the processor, can cause the device to: calculate a collision index between the host vehicle and the target vehicle, wherein the collision index indicates the possibility of a collision between the host vehicle and the target vehicle; and determine whether a collision is likely to occur based on the calculated collision index. The device, wherein the instructions, when executed by the processor, can cause the device to: determine that a collision is likely to occur based on the calculated collision index being 1.

[0009] The device, wherein the instructions, when executed by the processor, can cause the device to: determine that avoiding a collision between the vehicle and the target vehicle by steering is applicable based on the improbability of a collision, and set the autonomous driving of the vehicle to the first avoidance mode based on the applicable avoiding a collision by steering; or determine that avoiding a collision by steering is not applicable based on the high probability of a collision, and set the autonomous driving of the vehicle to the second avoidance mode based on the applicable avoiding a collision by steering.

[0010] The device, wherein the instructions, when executed by the processor, can cause the device to: based on the first avoidance mode, control the autonomous driving of the host vehicle to operate according to a basic function that does not require an additional deceleration amount for the autonomous driving of the host vehicle. The device, wherein the instructions, when executed by the processor, can cause the device to: based on the second avoidance mode, control the autonomous driving of the host vehicle to operate according to an extended function that can obtain an additional deceleration amount for the host vehicle.

[0011] According to the present disclosure, a method for controlling autonomous driving of a vehicle executed by a processor may include: receiving sensor information from at least one of a plurality of sensors installed in the vehicle; determining, based on the sensor information, whether other vehicles traveling within a threshold distance from the vehicle meet a target condition; setting the other vehicles as target vehicles based on the other vehicles meeting the target condition; determining an avoidance condition between the target vehicle and the vehicle; and controlling the autonomous driving of the vehicle to operate in a first avoidance mode or a second avoidance mode based on the avoidance condition.

[0012] The method may further include: determining that the target condition is satisfied based on the length of the other vehicle being longer than a reference length and based on the width of the other vehicle being wider than a reference width. The method may further include: setting the collision type to the first collision type or the second collision type based on the satisfaction of the target condition and based on the calculated impact point between the host vehicle and the target vehicle.

[0013] The method may further include: setting the collision type to the first collision type based on the calculated collision point on the X-axis being within the side collision range of the target vehicle. The method may further include: setting the collision type to the second collision type based on the calculated collision point on the Y-axis being within the side collision range of the target vehicle. The method may further include: calculating a collision index between the host vehicle and the target vehicle, wherein the collision index indicates the possibility of a collision between the host vehicle and the target vehicle; and determining whether a collision is likely to occur based on the calculated collision index.

[0014] The method may further include: determining that a collision is likely to occur based on the calculated collision index being 1. The method may further include: setting the autonomous driving of the host vehicle to the first avoidance mode based on determining that avoiding a collision between the host vehicle and the target vehicle by steering based on the unlikely occurrence of a collision is applicable; or setting the autonomous driving of the host vehicle to the second avoidance mode based on determining that avoiding a collision by steering based on the likely occurrence of a collision is not applicable.

[0015] The method may further include: based on the first avoidance mode, controlling the autonomous driving of the host vehicle to operate according to a basic function that does not require an additional deceleration amount of the host vehicle. The method may further include: based on the second avoidance mode, controlling the autonomous driving of the host vehicle to operate according to an extended function that can ensure an additional deceleration amount of the host vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 An example of an autonomously traveling vehicle according to an example of the present invention is shown.

[0017] Figure 2 An example of target conditions according to an example of the present invention is shown.

[0018] Figure 3 , Figure 4 and Figure 5 Examples of collision points according to examples of the present invention are shown.

[0019] Figure 6 An example of a collision index according to an example of the present invention is shown.

[0020] Figure 7 An example of avoidance possibilities according to an example of the present invention is shown.

[0021] Figure 8 An example of a first avoidance mode according to an example of the present invention is shown.

[0022] Fig. 9 and Fig.10An example of a second avoidance mode according to an example of the present invention is shown.

[0023] Fig.11 An example of a control method of an autonomously traveling vehicle according to an example of the present invention is shown. DETAILED DESCRIPTION

[0024] Hereinafter, examples of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention belongs can easily implement these examples. However, the present invention can be implemented in various different forms and is not limited to the examples described herein. In order to clearly describe the present invention in the accompanying drawings, parts that are not related to the description are omitted, and similar parts are represented by similar reference numerals throughout the specification.

[0025] Throughout the specification, if a part "comprises" an element, it means that other elements may be further included, rather than excluding other elements, unless explicitly stated otherwise. Additionally or alternatively, components indicated by the same reference numerals throughout the specification refer to the same elements.

[0026] Figure 1 An example of an autonomously traveling vehicle according to an example of the present invention is shown.

[0027] refer to Figure 1 , an autonomous driving vehicle 10 according to an example of the present disclosure includes at least one sensor 110 , a safe driving module 130 , and a processor 150 .

[0028] At least one sensor 110 is installed on the autonomous vehicle 10. The sensor 110 is installed on the autonomous vehicle 10, and various sensor information about the surroundings of the autonomous vehicle 10 can be obtained when the autonomous vehicle 10 is traveling, and the obtained sensor information can be provided to the processor 150 or the safe driving module 130, which will be described below. Here, the sensor information may include various information between other vehicles traveling near the autonomous vehicle 10 (hereinafter, the autonomous vehicle will be referred to as the host vehicle 10 in the description). For example, the sensor information may include the distance between the host vehicle 10 and another vehicle, the relative speed of the other vehicle, the position of the other vehicle, obstacles, traffic light information, etc.

[0029] The sensor 110 may include a camera, a radar, a LiDAR, and a global positioning system (GPS). The sensor 110 may acquire at least a peripheral image of the host vehicle 10, a distance between the host vehicle 10 and another vehicle, a relative speed of another vehicle, a position of another vehicle, obstacles, and traffic lights through the camera, the radar, and the LiDAR, and acquire the current position of the host vehicle 10 through the GPS. However, it is not limited thereto.

[0030] The safe driving module 130 may generate a driving path (or global path) for autonomous driving of the host vehicle 10 under the control of the processor 150. The safe driving module 130 controls autonomous driving based on the generated driving route under the control of the processor 150. For example, if a destination is input, the safe driving module 130 may generate a driving route from the current position of the host vehicle 10 to the destination under the control of the processor 150, and control the host vehicle 10 to autonomously drive based on the generated driving route.

[0031] In this case, the safe driving module 130 can collect real-time traffic information obtained through detailed maps and / or wireless communications, driving information of the vehicle 10, sensor information of the vehicle 10, weather information, etc. under the control of the processor 150, and can quickly and accurately generate a real-time updated driving route by analyzing various collected information.

[0032] In addition, the safe driving module 130 may store a detailed map capable of distinguishing lanes in a database. The detailed map may be automatically updated in each scheduling period through wireless communication, or manually updated by a user. For example, the memory may include at least one memory type of flash memory, hard disk memory, microchip, card (e.g., secure digital (SD) card or electronic stream digital (XD) card), etc., and at least one memory type of random access memory (RAM), static RAM (SRAM), read-only memory (ROM), programmable ROM (PROM), electrically erasable PROM (EEPROM), magnetic RAM (MRAM), magnetic disk, and optical disk.

[0033] The processor 150 may receive information about one or more sensors 110 from the plurality of sensors 110 installed on the host vehicle 10, and may analyze other vehicles traveling around the host vehicle 10 based on the information about the sensors 110. For example, the processor 150 may generate a sensor fusion trajectory SFT around the host vehicle 10 or around the driving path by receiving sensor information in real time from the plurality of sensors 110 installed on the host vehicle 10 that autonomously travels while following the generated driving path.

[0034] The processor 150 may analyze another vehicle traveling around the host vehicle 10 or around a driving path, or surrounding obstacles of the host vehicle 10 based on the generated sensor fusion trajectory SFT.

[0035] As a result of the analysis, if the sensor fusion trajectory SFT satisfies a predetermined target condition, the processor 150 may set the sensor fusion trajectory SFT as a target vehicle.

[0036] Additionally or alternatively, if a target vehicle is set, the processor 150 may calculate a collision point between the target vehicle and the host vehicle 10 based on the target vehicle. The processor 150 may determine the type of collision based on the calculated collision point.

[0037] Additionally or alternatively, if at least one collision index between the host vehicle 10 and the target vehicle satisfies all predetermined reference indexes, the processor 150 may determine that the target vehicle has cut-in. A detailed example thereof will be described later.

[0038] Thereafter, the processor 150 may determine an avoidance condition between a predetermined target vehicle and the host vehicle 10 and control to operate in the first avoidance mode or the second avoidance mode in response to the determination result. This will be described later.

[0039] refer to Figure 2 The processor 150 can calculate the sensor fusion trajectory SFT or the area of ​​other vehicles (or the size of the measurement area, the size of the determination area, the calculation area size or the range of the evaluation area, etc.) based on the sensor information collected on the driving route of the vehicle 10 or the predicted driving route.

[0040] The target condition may include length information of the sensor fusion track SFT and width information of the sensor fusion track SFT. Here, the length information of the sensor fusion track SFT may be set based on the length of the vehicle, the X direction, or the direction in which the vehicle is traveling. In addition, the width information of the sensor fusion track SFT may be set based on the width of the vehicle, the Y direction, or a direction intersecting the direction in which the vehicle is traveling.

[0041] If the analysis result shows that the length L0 of the sensor fusion trajectory SFT is longer than the predetermined reference length Threshold2 (threshold two) of the sensor fusion trajectory SFT, and the width W0 of the sensor fusion trajectory SFT is wider than the predetermined reference width Threshold1 (threshold one) of the sensor fusion trajectory SFT, the processor 150 can determine that the predetermined target condition is met, and can set the sensor fusion trajectory SFT as the target vehicle 11 based on the determination result.

[0042] Here, the predetermined reference length Threshold2 of the sensor fusion trajectory SFT may be set to about 5 m, and the predetermined reference width Threshold1 of the sensor fusion trajectory SFT may be set to about 2 m.

[0043] In other words, according to the analysis results, if the length L0 of the other vehicle is longer than the predetermined reference length Threshold2 of the other vehicle, and the width W0 of the other vehicle is wider than the predetermined reference width Threshold1 of the other vehicle, the processor 150 can determine that the predetermined target conditions are met, and can set the other vehicle as the target vehicle 11 based on the determination result.

[0044] For example, if the analysis result satisfies both the situation that the length L0 of the other vehicle is longer than the predetermined reference length Threshold2 of the other vehicle and the situation that the width W0 of the other vehicle is wider than the predetermined reference width Threshold1 of the other vehicle, the processor 150 can set the size index S to "1".

[0045] Here, the target vehicle 11 may be defined as a vehicle having a longer length and a wider width than a general vehicle. For example, the target vehicle 11 may include a trailer, a bus, a truck, etc., which are long and wide vehicles.

[0046] refer to Figure 3 The processor 150 may calculate a collision point between the host vehicle 10 and the determined target vehicle 11, and may set a collision type based on the calculated collision point. The collision type may include a first collision type and a second collision type.

[0047] If it is predicted that the target vehicle 11 collides with the driving route or the predicted driving route of the host vehicle 10 when cutting in, the processor 150 can change the control time based on the collision point rather than the rear center of the target vehicle 11 by percentage (%) based on the X-axis and Y-axis under the collision state, with a value within a predetermined reference range.

[0048] Here, the collision point can be set using the coordinates of the four vertices of the target vehicle 11 relative to the host vehicle 10. The four vertex coordinates can be determined as X-axis coordinates and Y-axis coordinates based on the X-axis coordinates as the longitudinal direction of the host vehicle 10 and the Y-axis coordinates as the lateral direction of the host vehicle 10. The collision point is also called the coordinates of the collision position. Here, the collision point is also called the impact point.

[0049] For example, the maximum value of the X-axis may be the front bumper of the target vehicle 11, and the minimum value of the X-axis may be the rear bumper of the target vehicle 11. If the target vehicle 11 performs a cut-in from the right side of the host vehicle 10, the left value of the Y-axis (or the minimum value of the Y-axis) may be the front bumper of the target vehicle 11, and the right value of the Y-axis (or the maximum value of the Y-axis) may be the rear bumper of the target vehicle 11. On the other hand, if the target vehicle 11 cuts in (cuts in) from the left side of the host vehicle 10, the left value of the Y-axis (or the maximum value of the Y-axis) may be the rear bumper of the target vehicle 11, and the right value of the Y-axis (or the minimum value of the Y-axis) may be the front bumper of the target vehicle 11.

[0050] like Figure 3 As shown, the processor 150 can calculate the average value using the maximum and minimum values ​​of each X-axis coordinate and Y-axis coordinate based on the impact point (or the coordinates of the collision position) between the host vehicle 10 and the target vehicle 11. The average value of the X-axis can be expressed as X_val_center, and the average value of the Y-axis can be expressed as Y_val_center.

[0051] As described above, by calculating the average value, the processor 150 can quickly determine the collision point where the host vehicle 10 collides with the target vehicle 11 , and can change the control time based on the collision point instead of the rear center of the target vehicle 11 .

[0052] For example, if the collision point calculated based on the X-axis between the target vehicle 11 and the host vehicle 10 satisfies the side collision judgment range (Threshold 3) of the target vehicle 11, the processor 150 may be set as the first collision type.

[0053] On the other hand, if the collision point calculated based on the Y-axis between the target vehicle 11 and the host vehicle satisfies the side collision determination range (Threshold 4) of the target vehicle 11, the processor 150 may be set to the second collision type.

[0054] Additionally or alternatively, if the impact point calculated from the collision point between the target vehicle 11 and the host vehicle 10 based on the X-axis satisfies the side collision judgment range (Threshold 3) of the target vehicle 11, and if the impact point calculated from the collision point between the target vehicle 11 and the host vehicle 10 based on the Y-axis satisfies the side collision judgment range (Threshold 4) of the target vehicle 11, the processor 150 can set the collision index (index I) to 1.

[0055] The first collision type may be a type of side collision between the front bumper of the host vehicle 10 and the target vehicle 11, such as Figure 4In this case, the collision point is represented as the impact point at negative (-) 7% on the X-axis and positive (+) 68% on the Y-axis.

[0056] Additionally or alternatively, the second collision type may be a type of collision between the front bumper of the host vehicle 10 and the rear of the target vehicle 11, such as Figure 5 In this case, the collision point is represented as the impact point at positive (+) 75% on the X-axis and 0% on the Y-axis.

[0057] refer to Figure 6 The processor 150 may calculate at least one collision index between the host vehicle 10 and the target vehicle 11 , and may determine whether the target vehicle 11 has cut in based on the calculated collision index.

[0058] The processor 150 may calculate at least one collision index between the host vehicle 10 and the target vehicle 11 , and may determine the cut-in of the target vehicle 11 if the at least one calculated collision index is equal to or less than each predetermined reference index.

[0059] For example, the at least one collision index may include a first collision index, a second collision index, and a third collision index.

[0060] The first collision index may be defined as the time taken until the four points of the host vehicle 10 (or the four vertex coordinates of the host vehicle 10) enter the path area PA of the target vehicle 11. The first collision index is also referred to as TTIS. For example, if the first collision index between the host vehicle 10 and the target vehicle 11 is equal to or less than the set first reference index (Threshold 5), the processor 150 may determine that the target vehicle 11 has cut in.

[0061] The second collision index may be defined as the time taken until the four points of the target vehicle 11 (or the four vertex coordinates of the target vehicle 11) enter the lane of the host vehicle 10. The second collision index is also referred to as TTIT. For example, if the second collision index between the host vehicle 10 and the target vehicle 11 is equal to or less than the second reference index (Threshold 6), the processor 150 may determine that the target vehicle 11 has cut in.

[0062] If a collision between the host vehicle 10 and the target vehicle 11 is predicted, the third collision index may be defined as the time taken until a collision occurs. The third collision index is also referred to as TTC. For example, if the third collision index between the host vehicle 10 and the target vehicle 11 is equal to or less than a set third reference index (Threshold 7), the processor 150 may determine the cut-in of the target vehicle 11.

[0063] For example, if the first collision index between the host vehicle 10 and the target vehicle is lower than the set first reference index (Threshold5), if the second collision index between the host vehicle 10 and the target vehicle 11 is lower than the set second reference index (Threshold6), and if the third collision index between the host vehicle 10 and the target vehicle 11 is lower than the set third reference index (Threshold7), all of which are met, the processor 150 can determine that the target vehicle 11 has cut in and set the collision index C to "1".

[0064] Here, the indices from the first reference index to the third reference index may each have a different value. Not limited thereto, and in some cases, the indices from the first reference index to the third reference index may have the same value.

[0065] Figure 7 An example of avoidance possibilities according to an example of the present invention is shown. Figure 8 is a diagram for explaining a first avoidance mode according to an example of the present invention, and Fig. 9 and Fig.10 An example of a second avoidance mode according to an example of the present invention is shown.

[0066] refer to Figure 7 , the processor 150 may determine whether avoidance is possible based on sensor information collected from the driving route or predicted driving route of the host vehicle 10 .

[0067] The processor 150 may analyze sensor information collected from a driving route or a predicted driving route of the host vehicle 10 , and may determine avoidance conditions based on the analysis result.

[0068] The processor 150 may control to operate in the first avoidance mode or the second avoidance mode according to the result of the determined avoidance condition.

[0069] For example, if the possibility of a collision risk occurring is low as a result of the determination of the avoidance condition, the processor 150 may determine that steering avoidance is possible or applicable, and perform control to operate in the first avoidance mode.

[0070] In contrast, if the possibility of a collision risk occurring is high as a result of the determination of the avoidance condition, the processor 150 may determine that steering avoidance is impossible or inapplicable, and perform control to operate in the second avoidance mode.

[0071] The second avoidance mode may operate as an extended functionality by ensuring an additional amount of deceleration in situations where avoidance steering is not possible or applicable.

[0072] Here, if Figure 7As shown, the avoidance condition may be determined by generating areas having a predetermined width on both sides of the driving route or the predicted driving route of the host vehicle 10 and determining whether there is a steering avoidance possible area when a collision risk occurs.

[0073] refer to Figure 7 and Figure 8 If there is a steering avoidance area, the processor 150 can determine that steering avoidance is possible, thereby setting it to the first avoidance mode, and if there is no steering avoidance area due to the guardrail 20 or due to another vehicle 12, it can be determined that steering avoidance is impossible or impractical, thereby setting it to the second avoidance mode.

[0074] In the case of the first avoidance mode, the processor 150 may be operated as a basic function that may not ensure the additional deceleration amount of the host vehicle 10. For example, in the case of the first avoidance mode, the processor 150 may be controlled to operate as a basic function, wherein the maximum braking control amount may be -9.8 m / s 2 And the maximum deceleration amount may be 80 km / h. In the first avoidance mode, the processor 150 may set the avoidance index (index A) to "0".

[0075] refer to Figure 7 , Fig. 9 and Fig.10 In the second avoidance mode, the processor 150 may be operated as an extended function capable of ensuring an additional deceleration amount of the host vehicle 10. In this case, the maximum deceleration amount may be increased at a predetermined ratio. For example, in the second avoidance mode, the processor 150 may perform an extended function operation. The extended function operation may increase the maximum deceleration amount by approximately 25% compared to the basic function operation. For example, in the extended function operation, the maximum braking control amount may be -9.8 m / s 2 , the maximum deceleration amount may be 100 km / h. In the second avoidance mode, the processor 150 may set the avoidance index (index A) to "1".

[0076] In more detail, the processor 150 can generate an area with a predetermined width on both sides of the driving route or predicted driving route of the vehicle 10, and if at least multiple avoidance conditions are met in the generated area, the processor 150 can determine whether steering avoidance is impossible or impractical.

[0077] like Figure 7 As shown, under the control of the processor 150, the host vehicle 10 can detect multiple front radar tracks ( Figure 7In this case, the processor 150 may determine that steering avoidance is impossible based on at least one avoidance condition that is a criterion for determining the guardrail 20.

[0078] For example, if the number of forward radar tracks in the area is greater than a first avoidance condition (Threshold 8), the predetermined longitudinal distance distribution of the forward radar tracks is greater than a second avoidance condition (Threshold 9), and the predetermined lateral distance distribution of the forward radar tracks is greater than a third avoidance condition (Threshold 10), the processor 150 may determine that steering to avoid is impossible or impractical.

[0079] For example, through the sensor information collected on the driving route or predicted driving route of the host vehicle 10, if there are sensor fusion trajectories SFT on both sides of the host vehicle 10, the processor 150 can determine that steering avoidance is impossible or impractical.

[0080] like Fig. 9 and Fig.10 As shown, if the guardrail 20 is present on the driving route or predicted driving route of the host vehicle 10, or if a long vehicle is traveling, the processor 150 can be set to the second avoidance mode and an additional deceleration amount can be ensured in advance, thereby performing earlier control.

[0081] Fig.11 An example of a method of controlling an autonomously traveling vehicle 10 according to an example of the present invention is shown.

[0082] refer to Fig.11 , a control method of an autonomous driving vehicle according to an example of the present invention is as follows.

[0083] The host vehicle 10 may receive information about at least one sensor 110 from the plurality of sensors 110 under the control of the processor 150 , and may determine the properties of a target vehicle traveling around the host vehicle 10 based on the information from the sensor 110 ( S11 ).

[0084] For example, if the sensor fusion trajectory meets a predetermined target condition, the host vehicle 10 may set the fusion trajectory of the sensor 110 as a target vehicle under the control of the processor 150 .

[0085] The vehicle 10, under the control of the processor 150, can calculate the sensor fusion trajectory SFT or the area (or size, dimension, etc.) of other vehicles based on the sensor information collected on the driving route or predicted driving route of the vehicle 10 (S12). This has been fully described above, so the description thereof will be omitted.

[0086] If the length L0 of the other vehicle is longer than a predetermined reference length Threshold2 of the other vehicle and the width W0 of the other vehicle is wider than a predetermined reference width Threshold1 of the other vehicle, the host vehicle 10 may set the size index S to “1” under the control of the processor 150 .

[0087] The host vehicle 10 may calculate the collision point between the host vehicle 10 and the determined target vehicle 11 under the control of the processor 150 (S13). This has been fully described above, so the description thereof will be omitted.

[0088] If the impact point calculated from the collision point between the target vehicle 11 and the host vehicle 10 based on the X-axis satisfies the side collision judgment range (Threshold3) of the target vehicle 11, and the impact point calculated from the collision point between the target vehicle 11 and the host vehicle 10 based on the Y-axis satisfies the side collision judgment range (Threshold4) of the target vehicle 11, then the host vehicle 10 can set the collision index I to "1" under the control of the processor 150.

[0089] If at least one collision index between the host vehicle 10 and the target vehicle 11 is equal to or less than each predetermined reference index, the host vehicle 10 may determine the target vehicle 11 as a cut-in (S14) under the control of the processor 150. This has been fully described above, so a description thereof will be omitted.

[0090] If the first collision index between the host vehicle 10 and the target vehicle 11 is equal to or less than the set first reference index (Threshold 5), the second collision index between the host vehicle 10 and the target vehicle 11 is equal to or less than the set second reference index (Threshold 6), and the third collision index between the host vehicle 10 and the target vehicle 11 is equal to or less than the set third reference index (Threshold 7), then the host vehicle 10 can determine to cut into the target vehicle 11 under the control of the processor 150. For example, if all three collision indexes are satisfied, then the host vehicle 10 can determine that the target vehicle 11 is cut into under the control of the processor 150, and set the collision index (index C) to "1".

[0091] If the set size index (index S), impact index (index I) and collision index (index C) are all set to "1", the vehicle 10 can determine the surrounding conditions of the vehicle 10 (S16) under the control of the processor 150 through sensor information collected in the driving path or predicted driving path of the vehicle 10.

[0092] Then, the host vehicle 10 under the control of the processor 150 may calculate whether avoidance is possible or actual (S17). The host vehicle 10 under the control of the processor 150 may be controlled to operate in the first avoidance mode or the second avoidance mode according to the calculated avoidance possibility.

[0093] If the collision risk is low, the host vehicle 10 may determine that steering avoidance is possible or applicable under the control of the processor 150, and may be controlled to operate in the first avoidance mode. For example, in the first avoidance mode, the host vehicle 10 may set the avoidance index (index A) to "0" under the control of the processor 150.

[0094] The host vehicle 10 may be operated in the first avoidance mode under the control of the processor 150 so as not to ensure a basic function of the additional deceleration amount of the host vehicle 10 .

[0095] On the other hand, if the possibility of a collision risk is high, the host vehicle 10 may determine that steering avoidance is impossible or inapplicable under the control of the processor 150, and control to operate in the second avoidance mode. In other words, in the second avoidance mode, the host vehicle 10 may set the avoidance index (index A) to "1" under the control of the processor 150.

[0096] In the second avoidance mode, the host vehicle 10 may be operated as an extended function capable of ensuring an additional deceleration amount of the host vehicle 10 under the control of the processor 150. In this case, the maximum deceleration amount may be increased at a predetermined ratio. For example, in the second avoidance mode, the processor 150 may perform an extended function operation. Compared with the basic function operation, the extended function operation may increase the maximum deceleration amount by approximately 25%.

[0097] The object of the present invention is to provide an autonomous driving vehicle and a control method thereof, which can sense the characteristics and cut-in situation of a long target through sensor signals, predict a collision with the vehicle based on the characteristics and cut-in situation, and perform braking for avoiding the collision.

[0098] The technical problems of the present invention are not limited to the above technical problems, and those skilled in the art will clearly understand other unmentioned technical problems through the following description.

[0099] In order to solve these problems, an example autonomous vehicle according to the present invention includes a processor, wherein the processor is configured to: receive at least one sensor information from a plurality of sensors installed on the vehicle, and based on the sensor information, analyze other vehicles traveling around the vehicle; set the other vehicles as target vehicles if they meet predetermined target conditions; determine an avoidance condition between the set target vehicle and the vehicle; and control the autonomous vehicle to operate in either a first avoidance mode or a second avoidance mode.

[0100] In at least one example of the present disclosure, the processor is further configured to: in response to the length of the other vehicle being longer than a predetermined reference length and the width of the other vehicle being wider than a predetermined reference width, determine that the target condition is met and set the other vehicle as the target vehicle.

[0101] In at least one example of the present disclosure, the processor is further configured to: if the target condition is met, calculate the impact point between the host vehicle and the target vehicle, and determine the collision type as the first collision type or the second collision type based on the calculated impact point.

[0102] In at least one example of the present disclosure, the processor is further configured to determine the collision type as the first collision type if the impact point determined based on the X-axis through the collision point between the target vehicle and the host vehicle is within the side collision judgment range of the target vehicle.

[0103] In at least one example of the present disclosure, the processor is further configured to determine the collision type as the second collision type if the impact point determined based on the Y-axis through the collision point between the target vehicle and the host vehicle is within the side collision judgment range of the target vehicle.

[0104] In at least one example of the present disclosure, the processor is further configured to calculate a collision index between the host vehicle and the target vehicle, and determine whether the target vehicle cuts in based on the calculated collision index.

[0105] In at least one example of the present disclosure, the processor is further configured to: if the calculated collision index is 1, determine that the target vehicle cuts in.

[0106] In at least one example of the present disclosure, the processor is further configured to: if the likelihood of a collision is low as a result of determining the avoidance condition, determine that steering to avoid is possible and set the autonomous vehicle to a first avoidance mode; and if the likelihood of a collision is high as a result of determining the avoidance condition, determine that steering to avoid is impossible and set the autonomous vehicle to a second avoidance mode.

[0107] In at least one example of the present disclosure, the processor is further configured to: in response to the first avoidance mode, control the autonomous vehicle to operate with a basic function, and the basic function may not use an additional deceleration amount of the autonomous vehicle.

[0108] In at least one example of the present disclosure, the processor is further configured to: if the autonomous vehicle is determined to be in the second avoidance mode, control the autonomous vehicle with an extended function, the extended function being capable of obtaining an additional deceleration amount of the autonomous vehicle.

[0109] According to another example of the present disclosure, a method for controlling an autonomous vehicle including a processor includes: receiving at least one sensor information from a plurality of sensors installed in the vehicle, and analyzing other vehicles traveling around the vehicle based on the sensor information; setting the other vehicles as target vehicles if the other vehicles meet predetermined target conditions; determining an avoidance condition between the set target vehicle and the vehicle; and controlling the autonomous vehicle to operate in a first avoidance mode or a second avoidance mode.

[0110] In at least one example method of the present disclosure, the method further includes: if the length of the other vehicle is longer than a reference length and the width of the other vehicle is wider than a reference width, determining that the target condition is satisfied and setting the other vehicle as a target vehicle.

[0111] In at least one example method of the present disclosure, the method further includes: if the target condition is satisfied, setting the collision type to the first collision type or the second collision type based on the calculated impact point between the host vehicle and the target vehicle.

[0112] In at least one example method of the present disclosure, the method further includes: if the impact point determined based on the X-axis through the collision point between the target vehicle and the host vehicle is within the side collision judgment range of the target vehicle, setting the collision type to the first collision type.

[0113] In at least one example method of the present disclosure, the method further includes: if the impact point determined based on the Y-axis through the collision point between the target vehicle and the host vehicle is within the side collision judgment range of the target vehicle, setting the collision type to the second collision type.

[0114] In at least one example method of the present disclosure, the method further includes: determining a collision index between the host vehicle and the target vehicle, and determining whether the target vehicle cuts in based on the calculated collision index.

[0115] In at least one example method of the present disclosure, the method further includes: if the calculated collision index is 1, determining that the target vehicle cuts in.

[0116] In at least one example method of the present disclosure, the method further includes: if as a result of determining the avoidance condition, the possibility of a collision risk is low, determining a first avoidance mode based on a result of determining that steering to avoid is possible; or if as a result of determining the avoidance condition, the possibility of a collision risk is high, determining a second avoidance mode based on a result of determining that steering to avoid is impossible.

[0117] In at least one example method of the present disclosure, the method further includes: operating in a basic function in the first avoidance mode, the basic function may not obtain an additional deceleration amount of the autonomously driven vehicle.

[0118] In at least one example method of the present disclosure, the method further includes: operating in the second avoidance mode with an extended function capable of ensuring an additional deceleration amount of the host vehicle.

[0119] The autonomous driving vehicle and control method thereof according to the present invention configured as described above can improve the reliability of the autonomous driving vehicle by sensing the characteristics of a long target vehicle and the cut-in situation of the target vehicle based on sensor signals, predicting a collision with the host vehicle based on sensor results, and performing braking control for avoiding the collision.

[0120] Additionally or alternatively, the autonomous vehicle and control method thereof according to the present disclosure can improve driving stability by determining a collision from the cut-in of a long target vehicle that has the possibility of emergency cut-in around the path of the autonomous vehicle, such as information such as size, impact point, collision time, etc., and performing braking to avoid collision.

[0121] Additionally or alternatively, the autonomous vehicle and control method thereof according to the present disclosure can determine the driving environment of the autonomous vehicle, and when it is determined that the situation is impossible to steer away from, perform an extended braking control function for further avoiding collision, thereby improving driving stability.

[0122] Additionally or alternatively, an autonomous driving vehicle and a control method thereof according to an example of the present invention can perform accurate control while reducing uncontrolled control and sensitive control by controlling based on a collision point when a target vehicle with a long length cuts in.

[0123] Additionally or alternatively, the autonomous driving vehicle and control method thereof according to the present disclosure can perform more agile and accurate control of the brakes when using an additional deceleration amount by determining the surrounding conditions in front of the vehicle.

[0124] Additionally or alternatively, the autonomous vehicle and control method thereof according to the present invention can determine the cut-in of a long target vehicle and determine whether to operate with a basic braking function or an extended braking function by using multiple indexes, such as calculation of the target size, calculation of the collision point with the target, calculation of the collision time with the target, calculation of the steering avoidance available area, etc., so that if the autonomous vehicle is robust, the control of the autonomous vehicle is insensitive, which improves the stability of the autonomous vehicle.

[0125] Effects obtainable from the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

[0126] The present invention described above can be implemented as a computer-readable code in a medium having a program recorded thereon. The computer-readable medium may include one or more types of recording devices in which data readable by a computer system is stored. For example, examples of computer-readable media include a hard disk drive (HDD), a solid state disk (SSD), a silicon disk drive (SDD), a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0127] Therefore, the above detailed description should not be interpreted as limiting in all examples, but should be regarded as illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent range of the present invention are included in the scope of the present invention.

Claims

1. A device for controlling autonomous driving of a vehicle, the device include: processor; and a memory storing instructions that, when executed by the processor, cause the apparatus to: receiving sensor information from at least one of a plurality of sensors mounted on the host vehicle; Based on the sensor information, determining whether other vehicles traveling within a threshold distance from the vehicle meet the target condition; Based on the other vehicles satisfying the target condition, setting the other vehicles as target vehicles; Determine the avoidance condition between the target vehicle and the host vehicle; as well as Based on the avoidance condition, autonomous driving of the host vehicle is controlled to operate in a first avoidance mode or a second avoidance mode.

2. The device according to claim 1, in, The instructions, when executed by the processor, cause the device to: Based on the length of the other vehicle being longer than a reference length, and based on the width of the other vehicle being wider than a reference width, it is determined that the target condition is satisfied.

3. The device according to claim 1, in, The instructions, when executed by the processor, cause the device to: Based on satisfying the target condition, calculating the collision point between the host vehicle and the target vehicle; as well as Based on the calculated impact point, the collision type is determined to be a first collision type or a second collision type.

4. The device according to claim 3, in, The instructions, when executed by the processor, cause the device to: Based on the calculated impact point on the X-axis being within the side collision range of the target vehicle, the collision type is determined to be the first collision type.

5. The device according to claim 3, in, The instructions, when executed by the processor, cause the device to: Based on the calculated impact point on the Y-axis being within the side collision range of the target vehicle, the collision type is determined to be the second collision type.

6. The device according to claim 1, in, The instructions, when executed by the processor, cause the device to: calculating a collision index between the host vehicle and the target vehicle, wherein the collision index indicates a possibility of collision between the host vehicle and the target vehicle; and Whether the possibility of a collision occurring is high is determined based on the calculated collision index.

7. The device according to claim 6, in, The instructions, when executed by the processor, cause the device to: Based on the calculated collision index being 1, it is determined that the possibility of the collision occurring is high.

8. The device according to claim 1, in, The instructions, when executed by the processor, cause the device to: determining that avoiding a collision between the host vehicle and the target vehicle by steering is applicable based on a low probability of a collision, and setting autonomous travel of the host vehicle to the first avoidance mode based on that avoiding a collision by steering is applicable; or Based on the high probability of a collision, it is determined that collision avoidance by steering is not applicable, and based on the fact that collision avoidance by steering is not applicable, autonomous travel of the host vehicle is set to the second avoidance mode.

9. The device according to claim 1, in, The instructions, when executed by the processor, cause the device to: Based on the first avoidance pattern, autonomous travel of the host vehicle is controlled to operate according to a basic function that does not require an additional amount of deceleration for autonomous travel of the host vehicle.

10. The device according to claim 1, in, The instructions, when executed by the processor, cause the device to: Based on the second avoidance mode, the autonomous travel of the host vehicle is controlled to operate according to an extended function capable of ensuring an additional deceleration amount of the host vehicle.

11. A method for controlling autonomous driving of a vehicle executed by a processor, the method The following steps are involved: receiving sensor information from at least one of a plurality of sensors installed in the host vehicle; Based on the sensor information, determining whether other vehicles traveling within a threshold distance from the vehicle meet the target condition; Based on the other vehicles satisfying the target condition, setting the other vehicles as target vehicles; Determine the avoidance condition between the target vehicle and the host vehicle; as well as Based on the avoidance condition, autonomous driving of the host vehicle is controlled to operate in a first avoidance mode or a second avoidance mode.

12. The method according to claim 11, further comprising: The following steps are involved: Based on the length of the other vehicle being longer than a reference length, and based on the width of the other vehicle being wider than a reference width, it is determined that the target condition is satisfied.

13. The method according to claim 11, further comprising: The following steps are involved: Based on the target condition being satisfied and based on the calculated impact point between the host vehicle and the target vehicle, the collision type is set to the first collision type or the second collision type.

14. The method according to claim 13, further comprising: The following steps are involved: The collision type is set to the first collision type based on the calculated collision point on the X-axis being within the side collision range of the target vehicle.

15. The method according to claim 13, further comprising: The following steps are involved: The collision type is set to the second collision type based on the calculated collision point on the Y-axis being within the side collision range of the target vehicle.

16. The method according to claim 11, further comprising: The following steps are involved: calculating a collision index between the host vehicle and the target vehicle, wherein the collision index indicates a possibility of collision between the host vehicle and the target vehicle; and Whether the possibility of a collision occurring is high is determined based on the calculated collision index.

17. The method according to claim 16, further comprising: The following steps are involved: Based on the calculated collision index being 1, it is determined that the possibility of the collision occurring is high.

18. The method according to claim 11, further comprising: The following steps are involved: setting the autonomous travel of the host vehicle to the first avoidance mode in response to determining that avoiding a collision between the host vehicle and the target vehicle by steering based on a low probability of a collision is appropriate; or The autonomous travel of the host vehicle is set to the second avoidance mode in accordance with a determination that collision avoidance by steering is not applicable based on a high probability of a collision.

19. The method according to claim 11, further comprising: The following steps are involved: Based on the first avoidance pattern, autonomous travel of the host vehicle is controlled to operate according to a basic function that does not require an additional amount of deceleration of the host vehicle.

20. The method according to claim 11, further comprising: The following steps are involved: Based on the second avoidance mode, the autonomous travel of the host vehicle is controlled to operate according to an extended function capable of ensuring an additional deceleration amount of the host vehicle.