Vehicle for searching for road shoulder parking position during automatic driving and method of operating same

Abstract

There is provided an autonomous vehicle including: at least one sensor configured to detect a surrounding environment of the vehicle and generate surrounding environment information; a processor configured to generate vehicle state information by monitoring a state of the vehicle during autonomous driving of the vehicle, and determine whether minimum risk maneuver (MRM) is required according to at least one of the ambient environment information and the vehicle state information; and a controller configured to control an operation of the vehicle under control of the processor, where the processor is configured to determine an MRM type based on a determination that an MRM is needed, and the processor is configured to generate at least one parking position candidate group when the determined MRM type is a road shoulder parking.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to and the benefit of Korean Patent Application No. 10-2023-0093085, filed on Jul. 18, 2023, which is incorporated herein by reference in its entirety. Background Art

[0003] In order to assist the vehicle driver in driving the vehicle, some advanced driver assistance systems (ADAS) are being developed. ADAS has multiple technical subcategories and provides convenient functions and / or operations for the driver. Such ADAS is also called autonomous driving or automated driving system (ADS).

[0004] At the same time, when the vehicle is driving automatically, the automatic driving system may also have abnormalities. If appropriate measures are not taken for such abnormalities in the automatic driving system, the vehicle may be in a dangerous state. Summary of the invention

[0005] The following summary presents a simplified summary of certain features. The summary is not an extensive overview, nor is it intended to identify key or essential elements.

[0006] Thus, various examples of the present disclosure disclose a vehicle that searches for an optimal parking location when shoulder parking is required as a minimal risk maneuver during autonomous driving.

[0007] The present disclosure provides a method of operating a vehicle that searches for an optimal parking location when a shoulder stop is required as a minimal risk maneuver during automated driving.

[0008] The technical problems to be solved by the present disclosure are not limited to the above technical problems. A person skilled in the art may know other technical problems not explicitly mentioned herein through the present disclosure.

[0009] A vehicle may include: at least one sensor configured to detect the surroundings of the vehicle and generate surrounding information; a processor configured to generate vehicle state information by monitoring the state of the vehicle during automatic driving of the vehicle, and determine whether a minimum risk maneuver (MRM) is required based on at least one of the surrounding information and the vehicle state information; and a controller configured to control the operation of the vehicle under the control of the processor, wherein, based on determining that MRM is required, the processor is configured to determine the MRM type, and when the determined MRM type is shoulder parking, the processor is configured to generate at least one parking position candidate group.

[0010] The processor may be configured to: identify a shoulder area based on surrounding environment information, divide the shoulder area into a plurality of virtual areas, determine a score for each virtual area, wherein the score is determined based on at least one of the following conditions: a speed of the vehicle, a free space on the shoulder area, and a distance from a current position of the vehicle to a parking position of the vehicle, and generate at least one parking position candidate group based on the determined score for each virtual area.

[0011] The processor may be configured to assign a predetermined score to a virtual area including the obstacle among the plurality of virtual areas.

[0012] The processor may be configured to: match a virtual window area corresponding to a size of the vehicle with the plurality of virtual areas; and generate at least one parking position candidate group based on a value obtained by summing scores of respective virtual areas included in the virtual window area.

[0013] The processor may be configured to, after generating at least one parking position candidate group, generate a path from a current position of the vehicle to each parking position candidate of the at least one parking position candidate group.

[0014] The processor may be configured to select the final parking position based on at least one of a travel distance of a path from the current position to each parking position candidate, a parking characteristic of the vehicle after following the path from the current position to each parking position candidate, and a value obtained by adding scores of a virtual area of ​​an area occupied by the vehicle after following the path from the current position to each parking position candidate.

[0015] The processor may be configured to generate, based on the stored map data, a first selection score for each travel distance based on a path from the current location to the corresponding parking location candidate.

[0016] The processor may be configured to generate a second selection score for each parking characteristic of the vehicle after following a path from the current location to the corresponding parking location candidate based on the stored map data.

[0017] The processor may be configured to generate a final score for the corresponding parking position candidate based on the first selection score, the second selection score, and a third selection score obtained by adding scores of respective virtual areas of the vehicle occupancy area after following a path from the current position to the corresponding parking position candidate, and select, among the final scores of the corresponding parking position candidates, a parking position candidate having a highest final score as the final parking position.

[0018] The processor may be configured to send a path following control command to the controller for the final parking position.

[0019] The processor may be configured to generate a parking position candidate group for changing the parking position based on determining that the vehicle fails to reach the final parking position within a preset time.

[0020] The operating method of a vehicle may include: during automatic driving of the vehicle: generating surrounding environment information by detecting the surrounding environment of the vehicle; generating vehicle status information by monitoring the status of the vehicle; determining whether a minimum risk maneuver (MRM) is required based on at least one of the surrounding environment information and the vehicle status information; and determining an MRM type based on determining that an MRM is required, and generating at least one parking position candidate group when the determined MRM type is shoulder parking.

[0021] Generating at least one parking position candidate group may include: dividing the shoulder area into a plurality of virtual areas based on the shoulder area identified from the surrounding environment information; determining a score for each virtual area, wherein the score is determined based on at least one of the following conditions: a speed of the vehicle, a free space on the shoulder area, or a distance from a current position of the vehicle to a parking position of the vehicle, and generating at least one parking position candidate group based on the determined score for each virtual area.

[0022] Generating at least one parking position candidate group may include: matching a virtual window area corresponding to a size of the vehicle with a plurality of virtual areas; and generating at least one parking position candidate group based on a value obtained by summing scores of respective virtual areas included in the virtual window area.

[0023] The operating method may further include, after generating the at least one parking position candidate group, generating a path from the current position of the vehicle to each parking position candidate of the at least one parking position candidate group.

[0024] The operating method may further include, after generating a path from a current position of the vehicle to each parking position candidate in the at least one parking position candidate group, selecting a final parking position based on at least one of a travel distance of the path from the current position to each parking position candidate, a parking characteristic of the vehicle after following the path from the current position to each parking position candidate, and a value obtained by adding scores of a virtual area of ​​an occupied area of ​​the vehicle after following the path from the current position to each parking position candidate.

[0025] Selecting the final parking position may include: generating a first selection score for each travel distance based on a path from the current position to the corresponding parking position candidate based on the stored map data; generating a second selection score for each parking characteristic of the vehicle following the path from the current position to the corresponding parking position candidate based on the stored map data; and generating a third selection score by adding scores of respective virtual areas of the vehicle occupancy area following the path from the current position to the corresponding parking position candidate.

[0026] The operating method may further include: after generating the third selection score: generating a final score for the corresponding parking position candidate based on the first selection score, the second selection score and the third selection score; and selecting, among the final scores of the corresponding parking position candidate, a parking position candidate with a highest final score as the final parking position.

[0027] The operating method may further include: after selecting the final parking position, controlling the vehicle to follow a path to the final parking position.

[0028] The operating method may further include: after controlling the vehicle to follow the path to the final parking position, generating a parking position candidate group for changing the parking position based on determining that the vehicle fails to reach the final parking position within a preset time.

[0029] These features and other advantages are described in more detail below. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a block diagram of exemplary components of a vehicle;

[0031] Figure 2 is a block diagram of the processor;

[0032] Figure 3 Show the minimum risk maneuver (MRM) strategy for each state of the vehicle;

[0033] Figure 4A and 4B An example is shown in which a vehicle determines an MRM strategy based on surrounding environment information within a specified MRC range, wherein;

[0034] Figure 5 An example of changing the MRM strategy priority according to surrounding object information within a specified MRC range in a vehicle is shown;

[0035] Fig. 6A , 6B and 6C show an example in which a vehicle determines whether its own vehicle collides with a nearby vehicle through MRM;

[0036] Figure 7 An example is shown in which a vehicle determines an MRM strategy of its own vehicle by considering whether it will collide with a nearby vehicle through its own vehicle's MRM;

[0037] Fig. 8A and 8B An example showing a vehicle calculating distances to nearby vehicles;

[0038] Fig. 9 is a flow chart illustrating the operation of the vehicle;

[0039] Fig.10is a flow chart showing a vehicle determining an MRM strategy;

[0040] Fig.11 is a flow chart illustrating a road shoulder parking operation during automated driving;

[0041] Fig.12 An example showing a vehicle meshing a shoulder area;

[0042] Fig.13 An example of a vehicle generating a candidate set of optimal parking positions is shown;

[0043] Fig.14 An example of a candidate group of optimal parking positions is shown;

[0044] Fig.15 An example showing a vehicle generating an optimal path; and

[0045] Fig.16 and 17 An example of a vehicle generating a group of optimal parking position candidates is shown. DETAILED DESCRIPTION

[0046] Hereinafter, various examples of the present disclosure will be described in detail with reference to the accompanying drawings.

[0047] The details of the structure of the present disclosure and the effects generated thereby will be more clearly understood through the following detailed description. Before describing the present disclosure in detail, the same parts are also represented by the same reference numerals as much as possible, even if the same parts are described in different drawings. It should be noted that the detailed description may be omitted when the known configuration may make the subject matter of the present disclosure unclear.

[0048] Before describing the present disclosure in detail, the terms used in the present disclosure may be explained and / or defined as follows.

[0049] The vehicle may be equipped with an automated driving system (ADS) and may drive automatically. For example, the vehicle may perform at least one of steering, acceleration, deceleration, lane change, and parking through the ADS (e.g., without driver manipulation). The ADS may include at least one of the following: a pedestrian detection and collision mitigation system (PDCMS), a lane change decision assistance system (LCAS), a lane departure warning system (LDWS), an adaptive cruise control system (ACC), a lane keeping assist system (LKAS), a road boundary departure prevention system (RBDPS), a curve speed warning system (CSWS), a forward vehicle collision warning system (FVCWS), a low speed follow system (LSF), etc.

[0050] The driver may be a person who uses the vehicle and receives services from the autonomous driving system.

[0051] The vehicle control mechanism may control at least one component of the vehicle and / or at least one function of the vehicle. The at least one function of the vehicle may include, for example, a steering function, an acceleration function, a deceleration function (or a braking function), a lane change function, a lane detection function, a lateral control function, an obstacle recognition and distance detection function, a power system control function, a safety zone detection function, an engine on / off function, a power on / off function, and a vehicle lock / unlock function. The listed vehicle functions are merely examples for understanding, and the embodiments of the present disclosure are not limited thereto.

[0052] The shoulder (or shoulder area) may refer to the space between the outermost road boundary (outermost lane boundary) in the vehicle travel direction and the road edge (eg, curbstone, guardrail).

[0053] Figure 1 is a block diagram of an example vehicle. Each component of the vehicle (eg, including electronic devices) may be configured by means of one chip, one part, or one electronic circuit, or the component may be configured by combining chips, parts, and / or electronic circuits. Figure 1 Some of the components shown may be divided into multiple components and may be configured by means of different chips, parts or electronic circuits. In addition, some components may be combined and configured by means of one chip, one part or one electronic circuit. Figure 1 Some of the components shown in the figure may be added, or components not shown may be added. Figure 2 To 8 description Figure 1 at least some parts of . Figure 2 It is a functional block diagram of the processor. Figure 3 The minimum risk maneuver (MRM) strategy for each state of the vehicle is shown. Figure 4A and 4B An example is shown in which a vehicle determines an MRM strategy based on surrounding environment information within a specified MRC range. Figure 5 An example of changing the MRM strategy priority based on surrounding object information within a specified MRC range in a vehicle is shown. Figures 6A to 6C An example is shown in which a vehicle determines whether its own vehicle has collided with a nearby vehicle through the MRM. Figure 7 An example is shown in which a vehicle determines the MRM strategy of its own vehicle by using the MRM of its own vehicle while considering whether there will be a collision with a nearby vehicle. Fig. 8A and 8B An example of a vehicle calculating the distance to nearby vehicles is shown.

[0054] Reference Figure 1 , the vehicle 100 may include a sensor unit 110 (eg, including one or more sensors), a controller 120 , a processor 130 , a display 140 , a communication device 150 , and a memory 160 .

[0055] The sensor unit 110 may detect the surrounding environment of the vehicle 100 by using at least one sensor, and may generate data related to the surrounding environment according to the detection result. Based on the sensing data obtained from the at least one sensor, the sensor unit 110 may obtain road information, information of objects around the vehicle (e.g., other vehicles, people, objects, curbs, guardrails, lanes, obstacles), and / or vehicle position information. The road information may include, for example, at least one of the following: lane position, lane shape, lane color, lane type, number of lanes, whether there is a shoulder or the size of the shoulder. The objects around the vehicle may include, for example, at least one of the following: the position of the object, the size of the object, the shape of the object, the distance to the object, and the speed relative to the object.

[0056] The sensor unit 110 may include at least one of the following: a camera, a light detection and ranging (LIDAR), a radio detection and ranging (RADAR), an ultrasonic sensor, an infrared sensor, and a position measurement sensor. The listed sensors are examples for understanding purposes only, and the sensors included in the sensor unit 110 of the present disclosure are not limited thereto. The camera may capture the surrounding environment of the vehicle and may generate image data, which includes lanes and / or surrounding objects at the front, rear, and / or sides of the vehicle 100. LIDAR may generate information about objects located at the front, rear, and / or sides of the vehicle 100 by using light (or laser). RADAR may generate information about objects located at the front, rear, and / or sides of the vehicle 100 by using electromagnetic waves (or radio waves). An ultrasonic sensor may generate information about objects located at the front, rear, and / or sides of the vehicle 100 by using ultrasonic waves. An infrared sensor may generate information about objects located at the front, rear, and / or sides of the vehicle 100 by using infrared light. The position measurement sensor may measure the current position of the vehicle 100. The position measurement sensor may include at least one of a global positioning system (GPS) sensor, a differential global positioning system (DGPS) sensor, and a global navigation satellite system (GNSS) sensor. The position measurement sensor may generate vehicle position data based on a signal generated by at least one of the GPS sensor, the DGPS sensor, and the GNSS sensor.

[0057] The controller 120 may control the operation of at least one component of the vehicle 100 and / or at least one function of the vehicle under the control of the processor 130. The at least one function may include, for example, a steering function, an acceleration function (or a longitudinal acceleration function), a deceleration function (or a longitudinal deceleration function, a braking function), a lane change function, a lane detection function, an obstacle recognition and distance detection function, a lateral control function, a powertrain control function, a safety zone detection function, an engine on / off function, a power on / off function, and a vehicle lock / unlock function.

[0058] The controller 120 may control the operation of the vehicle and / or at least one function of the vehicle and / or at least one component of the vehicle under the control of the processor 130 for the purpose of autonomous driving and / or minimum risk maneuvering (MRM) of the vehicle 100. For example, the controller 120 may control the operation of at least one of the following: a steering function, an acceleration function, a deceleration function, a lane change function, a lane detection function, a lateral control function, an obstacle recognition and distance detection function, a power system control function, and a safety zone detection function.

[0059] The processor 130 may control the overall operation of the vehicle 100. The processor 130 may include an electronic control unit (ECU) capable of overall control of components within the vehicle 100. For example, the processor 130 may include a central processing unit (CPU) or a microprocessing unit (MCU) capable of performing computational processing.

[0060] Processor 130 may control components in vehicle 100 so that the vehicle performs autonomous driving by activating an automated driving system (ADS) when a specified event occurs. The specified event may occur when the driver is required to perform autonomous driving, when the driver takes control of the vehicle, or when conditions specified by the driver and / or designer are met.

[0061] The processor 130 may determine whether normal autonomous driving is possible according to at least one of vehicle state information and surrounding environment information during autonomous driving. If normal autonomous driving is not feasible (e.g., impossible), the processor 130 may determine an MRM strategy and may control the determined MRM strategy to be executed. Here, the MRM strategy may include an MRM type.

[0062] like Figure 2 As shown, the processor 130 may include a vehicle state information acquiring unit 1310 , a surrounding environment information acquiring unit 1320 , and an MRM strategy determining unit 1330 .

[0063] The vehicle status information acquisition unit 1310 may monitor the mechanical and / or electrical status of various components in the vehicle (e.g., sensors, ADS processors, actuators, etc.) from the time when the ADS is enabled, and may acquire vehicle status information indicating whether a mechanical failure and / or electrical failure occurs in the components in the vehicle. The vehicle status information may include information about the mechanical and / or electrical status of the components in the vehicle. For example, the vehicle status information may include the following information: the information indicates whether the functions required for autonomous driving can operate normally according to the mechanical and / or electrical status of the components in the vehicle.

[0064] The surrounding environment information acquisition unit 1320 may acquire information about the surrounding environment of the vehicle from the point in time when the ADS is enabled by using the sensor unit 110 and / or the communication device 150. The surrounding environment information acquisition unit 1320 may include a road information acquisition unit 1321 that acquires information about a road on which the vehicle is traveling, and a surrounding object information acquisition unit 1322 that detects objects around the vehicle through the sensor unit 110.

[0065] The road information acquisition unit 1321 may acquire road information about where the vehicle is traveling through the sensor unit 110. The road information acquisition unit 1321 may acquire map information from an external device (e.g., another vehicle or a server) through the communication device 150, and may acquire road information about where the vehicle is traveling based on the map information.

[0066] The surrounding object information acquisition unit 1322 may acquire information about objects (e.g., other vehicles, people, objects, curbs, guardrails, lanes, obstacles) around the vehicle through the sensor unit 110. For example, the surrounding object information acquisition unit 1322 may obtain the distance and relative speed to at least one vehicle located in front of, to the side of, and / or behind the vehicle.

[0067] The processor 130 may determine whether the functions required for autonomous driving can be operated normally based on the vehicle state information. The functions required for autonomous driving may include, for example, at least one of the following: a lane detection function, a lane change function, a lateral control function, a deceleration (or braking control) function, a power system control function, a safety area detection function, an obstacle recognition and distance detection function. If at least one function required for autonomous driving cannot be operated normally, the processor 130 may determine that normal autonomous driving is not feasible (e.g., impossible).

[0068] The processor 130 may determine whether the state of the vehicle is suitable for general driving conditions based on the vehicle state information. For example, the processor 130 may determine whether the mechanical state information of the vehicle (e.g., tire pressure information or engine overheating information) is suitable for general driving conditions. If the state of the vehicle is not suitable for general driving conditions, the processor 130 may determine that normal autonomous driving is not feasible (e.g., impossible). For example, if normal driving of the vehicle is not feasible (e.g., impossible) due to tire pressure or engine overheating, the processor 130 may determine that normal autonomous driving is not feasible (e.g., impossible).

[0069] Based on at least one of the plurality of pieces of surrounding environment information, the processor 130 may determine whether the environment around the vehicle is suitable for an operation design domain (ODD) of autonomous driving. The operation design domain may represent surrounding environment conditions under which autonomous driving operates normally. If the vehicle surrounding environment information does not meet the operation design domain, the processor 130 may determine that normal autonomous driving is not feasible (e.g., impossible).

[0070] If normal autonomous driving is not feasible (e.g., impossible), the processor 130 may determine that it is necessary to perform a minimum risk maneuver to minimize the risk of an accident. If it is determined that a minimum risk maneuver is required, the processor 130 may select a minimum risk maneuver strategy from a plurality of minimum risk maneuver strategies by using the MRM strategy determination unit 1330. The minimum risk maneuver strategy may include (e.g., Figure 3 For example, the minimum risk maneuvering strategy may include a traffic lane stop 301 strategy including type 1 and type 2, and may include a road shoulder stop 303 strategy including type 3 and type 4.

[0071] Traffic lane parking 301 strategies may include type 1 straight line parking 311 and type 2 in-lane parking 312. Road shoulder parking 303 strategies may include type 3 half shoulder parking 313 and type 4 full shoulder parking 314.

[0072] The straight-line parking 311 of type 1 is a type in which the vehicle is stopped using only the braking control 323 (longitudinal deceleration function). The straight-line parking 311 does not involve lateral control. For example, the straight-line parking 311 may be performed in a case where at least one of the following is not feasible: lateral control 321, power system control 322, lane change 324, and detection of a potential parking position outside the traffic lane 325. For example, the straight-line parking may be performed in a case where lateral control is not feasible (e.g., impossible) and lane detection is not feasible (e.g., impossible) due to an actuator failure. Here, the detection of a potential parking position outside the traffic lane may be a function of detecting a position of a safety zone located outside the traffic lane, such as a shoulder or a rest stop.

[0073] Type 2 in-lane stop 312 is a type in which the vehicle stops within the boundaries of the lane in which the vehicle is traveling. For example, in-lane stop 312 may refer to a type in which the vehicle stops within the boundaries of the lane in which the vehicle is traveling by lateral control 321 and / or brake control 323. The lane in which the vehicle is traveling may refer to a lane in which the vehicle is traveling at the point in time when it is determined that the minimum risk maneuver is necessary. In-lane stop 312 may be performed when at least one of powertrain control 322, lane change 324, or detection of a potential parking position outside of a traffic lane 325 is not possible.

[0074] The type 3 half shoulder stop 313 is a type in which the vehicle stops in a state in which a part of the vehicle is located on the shoulder of the road. For example, the half shoulder stop 313 may refer to a type in which the vehicle is stopped by lateral control 321, brake control 323, lane change 324, and / or detection of a potential parking position outside a traffic lane 325 so that a part of the vehicle is located on the shoulder outside the road boundary (or outside the outermost lane boundary), and then the vehicle stops.

[0075] Type 4 full shoulder stop 314 refers to a type in which the vehicle stops with the entire vehicle located on the shoulder of the road. For example, full shoulder stop 314 may refer to a type in which the vehicle stops with the entire vehicle located on the shoulder outside the road boundary (or the outermost lane boundary) through lateral control 321, brake control 323, lane change 324, and / or detection of a potential parking position outside the traffic lane 325.

[0076] The priorities of the aforementioned MRM types may be determined based on the road, the surrounding environment, and the fault-operation capability of the vehicle to tolerate faults. For example, in order to minimize the parking risk, the MRM type corresponding to the road shoulder parking 303 strategy may have a higher priority than the traffic lane parking 301 strategy. In addition, the priority of the MRM type corresponding to the full shoulder road parking 314 may be set higher than the priority of the MRM type corresponding to the half shoulder road parking 313, and the priority of the MRM type corresponding to the lane parking 312 may be set higher than the priority of the MRM type corresponding to the straight line parking 311. That is, the priorities of the MRM types may be determined to be full shoulder parking 314, half shoulder parking 313, lane parking 312, and straight line parking 311.

[0077] The MRM policy determination unit 1330 of the processor 130 may select the MRM policy based on at least one of the vehicle state information and the surrounding environment information.

[0078] Among the functions required for the automatic driving based on the vehicle state information, there are functions that operate normally and / or functions that do not operate normally. The MRM strategy determination unit 1330 can check the executable MRM types among the above MRM types according to these functions. For example, when the lateral control function operates normally, the MRM strategy determination unit 1330 can determine that the straight-line parking 311, the parking in the lane 312, the half-shoulder parking 313, and the full-shoulder parking 314 among the executable MRM types are all executable. For another example, when the lateral control function does not operate normally, the executable MRM type can be determined as the straight-line parking 311.

[0079] If there is one executable MRM type checked according to the vehicle state information, the MRM strategy determination unit 1330 may determine the corresponding MRM type as the MRM strategy. For example, when the lateral control function does not operate normally, only the straight parking 311 may be executed. Therefore, the MRM strategy determination unit 1330 may determine the straight parking 311 as the MRM strategy. For another example, when the driving lane cannot be detected due to a sensor failure and / or an external environment, only the straight parking 311 may be executed. Therefore, the MRM strategy determination unit 1330 may determine the straight parking 311 as the MRM strategy.

[0080] If there are multiple MRM types that can be performed based on the vehicle state information, the MRM strategy determination unit 1330 can select an MRM type that can be performed within a specified minimum risk condition (MRC) range. The specified MRC range can be set and / or changed by an operator and / or designer. The specified MRC range can be set differently according to the performance of the vehicle, the type of vehicle, and / or external environmental factors (such as weather, time, etc.).

[0081] The MRM strategy determination unit 1330 may determine the MRM type executable within the MRC range according to whether there is a shoulder within the specified MRC range. If there is no shoulder within the specified MRC range, the MRM strategy determination unit 1330 may determine that the MRM types executable within the MRC range are lane parking 312 and straight line parking 311.

[0082] If there is a shoulder within the specified MRC range, the MRM strategy determination unit 1330 may determine the MRM type that can be executed within the MRC range according to the size of the shoulder. If the size of the shoulder within the specified MRC range is greater than or equal to the specified size, the MRM strategy determination unit 1330 may determine that the MRM types that can be executed within the MRC range are full shoulder parking 314, half shoulder parking 313, lane parking 312, and straight line parking 311. The specified size may be determined according to the size of the vehicle. If the shoulder size is less than the specified size, the MRM strategy determination unit 1330 may determine that the MRM types that can be executed within the MRC range are half shoulder parking 313, lane parking 312, and straight line parking 311.

[0083] If there are a plurality of executable MRM types within a specified MRC range, the MRM policy determination unit 1330 may select a final MRM policy in consideration of priority and / or surrounding object information.

[0084] If there are multiple MRM types that can be executed within the specified MRC range, the unit 1330 for determining the MRM policy can select an MRM type with the highest priority among the MRM types that can be executed within the specified MRC range as the final MRM policy. Figure 4AAs shown, when the shoulder width 410 within the specified MRC range 400 is greater than the vehicle width 100, the MRM strategy determination unit 1330 may select the full shoulder parking 314 with the highest priority as the final MRM strategy among the MRM types executable within the MRC range 400. Figure 4B As shown, when the width of the shoulder 420 within the specified MRC range 400 is less than the vehicle width 100, the MRM strategy determination unit 1330 may select the half shoulder parking 313 with the highest priority as the final MRM strategy among the MRM types executable within the MRC range 400.

[0085] The MRM strategy determination unit 1330 may select a final MRM strategy based on the implementation of the MRM strategy within the specified MRC range by additionally considering the risk level. Figure 5 As shown, it is assumed that there is a shoulder 501 within the MRC range 400, and in the area of ​​the shoulder 501 within the MRC range 400, the width of the area adjacent to the vehicle 100 is greater than the width of the vehicle 100, and the width of the area away from the vehicle 100 is less than the width of the vehicle 100. That is, it is assumed that there is a shoulder 501 with a gradually decreasing width within the MRC range 400. In this case, the MRM strategy determination unit 1330 may select the full shoulder stop 314 with the highest priority based on the width of the shoulder 501. However, during the execution of the full shoulder stop 314, if there is a risk 520 of collision (or rear-end collision) with another vehicle 510, the MRM strategy determination unit 1330 may select the following half shoulder stop 313 as the final RMR strategy: the priority of the half shoulder stop is lower than the priority of the full shoulder stop 314 and there is no risk of rear-end collision with another vehicle 510.

[0086] If there are multiple executable MRM types within the specified MRC range, the MRM strategy determination unit 1330 can select the final MRM strategy while considering whether there is a possibility of collision and accident liability. Based on the driving path of each type of MRM type that can be executed within the specified MRC range, the MRM strategy determination unit 1330 can determine the possibility of collision with nearby vehicles and whether there is accident liability in the event of collision. For full shoulder parking and / or half shoulder parking that requires lane change, the MRM strategy determination unit 1330 can determine the possibility of collision with nearby vehicles located in front, vehicles located on the side, and / or vehicles located behind the side of the own vehicle, and whether there is accident liability. For parking in a lane that does not require lane change, the MRM strategy determination unit 1330 can determine the possibility of collision with a vehicle located behind the vehicle near the own vehicle and whether there is accident liability.

[0087] In order to determine the possibility of collision with nearby vehicles and whether there is responsibility for the accident, the MRM strategy determination unit 1330 can calculate the following safety distance based on the responsibility-sensitive safety (RSS) model shown in the following equations 1 and 2, which represents the difference between the minimum relative distance to nearby vehicles and the actual relative distance to nearby vehicles, and can determine the possibility of collision and whether there is responsibility for the accident based on the calculated safety distance.

[0088] RSSx=d x -d min,x

[0089] RSSy=d y -d min,y

[0090] ......Equation (1)

[0091] Among them, RSSx represents the longitudinal safety distance, d min,x It indicates the minimum longitudinal relative distance that must be maintained with nearby vehicles, and d x Indicates the actual longitudinal relative distance between the vehicle and nearby vehicles. In addition, RSSy indicates the lateral safety distance, d min,y It indicates the minimum lateral relative distance that must be maintained with nearby vehicles, and d y Indicates the actual lateral relative distance between the own vehicle and nearby vehicles.

[0092] If at least one of the longitudinal safety distance RSSx and the lateral safety distance RSSy to the nearby vehicle is positive, the MRM strategy determination unit 1330 may determine that the possibility of collision with the nearby vehicle is low (or no), even when the MRM with the driving path related to the nearby vehicle is executed. In addition, the MRM strategy determination unit 1330 may determine that even if a collision with the nearby vehicle occurs, the own vehicle is not responsible for the accident. For example, if Fig. 6A As shown, when the longitudinal safety distance RSSx between the vehicle (own vehicle) 100 and the right front vehicle 601 is a negative value and the lateral safety distance RSSy is a positive value, the MRM strategy determination unit 1330 can determine that the possibility of collision with the right front vehicle 601 is low, even in the case of performing MRM requiring lane change (e.g., half shoulder parking and / or full shoulder parking), and can determine that the own vehicle 601 is not responsible for the accident even in the case of collision with the right front vehicle. For another example, if Figure 6BAs shown, the lateral safety distance RSSy from the vehicle (the own vehicle) 100 to the front vehicle 611 traveling in the same lane is a negative value, and the longitudinal safety distance RSSx is a positive value, then the MRM strategy determination unit 1330 can determine that the possibility of a collision with the front vehicle 611 is low, even when an MRM requiring a lane change (e.g., half shoulder parking and / or full shoulder parking) is performed, and can determine that the own vehicle is not responsible for the accident even in the event of a collision with the front vehicle 611.

[0093] If the longitudinal safety distance RSSx and the lateral safety distance RSSy to the nearby vehicle are both negative values, the MRM strategy determination unit 1330 may determine that the possibility of collision with the nearby vehicle is high (or possible) when executing the MRM with the driving path related to the nearby vehicle. In addition, the MRM strategy determination unit 1330 may determine that the own vehicle is responsible for the accident when a collision with the nearby vehicle occurs. For example, Figure 6C As shown, when the longitudinal safety distance RSSx and the lateral safety distance RSSy from the vehicle (own vehicle) 100 to the right front vehicle 621 are both negative values, the MRM strategy determination unit 1330 may determine that when the MRM requires a lane change (e.g., a half shoulder stop and / or a full shoulder stop), there is a high possibility of a collision with the right front vehicle 621. In addition, because the lane change of the own vehicle may result in a collision with the right front vehicle 621, the MRM strategy determination unit 1330 may determine that the own vehicle is responsible for the accident when a collision with the right front vehicle 621 occurs.

[0094] If it is determined that the possibility of collision with a nearby vehicle is high when performing an MRM requiring a lane change, the MRM strategy determination unit 1330 may select in-lane parking with a lower priority than full shoulder parking and half shoulder parking as the final MRM. Here, the MRM strategy determination unit 1330 may calculate the longitudinal safety distance and the lateral safety distance between the own vehicle and the rear vehicle traveling in the same lane. If at least one of the longitudinal safety distance and the lateral safety distance to the rear vehicle is a positive value, the MRM strategy determination unit 1330 may determine that even if in-lane parking is performed, the possibility of collision with the rear vehicle is low, and there is no accident liability even if a collision occurs, and then in-lane parking may be selected as the final MRM. For example, if Figure 7As shown, in the case where MRM needs to be performed, in order to make the full shoulder parking of type 4 have the highest priority, the vehicle (own vehicle) 100 can calculate the longitudinal and lateral safety distances to the side rear vehicle 720. However, if the longitudinal and lateral safety distances to the side rear vehicle 720 are both negative values, the possibility of collision with the side rear vehicle 720 is greater due to the lane change of the full shoulder parking, and the own vehicle may be responsible when the collision with the side rear vehicle 720 occurs. Therefore, because the longitudinal and lateral safety distances between the vehicle (own vehicle) 100 and the rear vehicle 710 are both positive values, the vehicle (own vehicle) 100 can select the type 2 lane parking with a lower priority than type 4 as the final MRM strategy.

[0095] The longitudinal and lateral safety distances between the own vehicle and nearby vehicles can be calculated by the following equations 2 and 3.

[0096] like Fig. 8A As shown, the following equation 2 is used to calculate the longitudinal safety distance Rss between the own vehicle Cr and the nearby vehicle Cf x 810. Figure 8B As shown, the following equation 3 is used to calculate the lateral safety distance Rss between the own vehicle Cr and the nearby vehicle Cf y 820 equation.

[0097]

[0098]

[0099] Here, "ρ" means the reaction time, and "μ" means the lateral edge. min,brake ” means the minimum deceleration of the own vehicle, and “a max,accel " means the maximum acceleration of nearby vehicles. "a max,brake ” means the maximum deceleration of nearby vehicles.

[0100] To calculate the lateral and / or longitudinal safety distances, the parameters of equations 2 and 3 may be set as shown in Table 1 below.

[0101] parameter value ρ 0.5(s) μ 0.4(m) <![CDATA[a max,brake ]]> <![CDATA[6(m / s 2 )]]> <![CDATA[a min,brake ]]> <![CDATA[8(m / s 2 )]]> <![CDATA[a max,accel ]]> <![CDATA[0(m / s 2 )]]> <![CDATA[a lat min,brake ]]> <![CDATA[4(m / s 2 )]]> <![CDATA[a lat max,accel ]]> <![CDATA[0(m / s 2 )]]>

[0102] Table 1

[0103] The parameter values ​​of Table 1 of various embodiments of the present disclosure are not limited thereto.

[0104] In order to select the final MRM strategy, the MRM strategy determination unit 1330 may store support data for selecting the final MRM strategy in the memory 160. The support data may include at least one of the following: the presence or absence of a shoulder within the specified MRC range, the size of the shoulder (e.g., length and / or width), the safety distance from nearby vehicles, vehicle state information of the own vehicle, or lane detection information. The MRM strategy determination unit 1330 stores support data for selecting the final MRM strategy, thereby ensuring the basis for selecting an MRM strategy with a lower priority. For example, when straight-line parking of type 1 is selected as the final MRM strategy, the MRM strategy determination unit 1330 may store at least one of the following in the memory 160: information indicating abnormal operation of the lateral control function, information indicating defects in the steering angle, steering speed, and lane detection sensor, or a sensed value of the lane detection sensor. For another example, if there is a shoulder within the specified MRC range and parking in the lane of type 2 is selected as the final MRM strategy, the MRM strategy determination unit 1330 may store longitudinal and lateral safety distance information about at least one nearby vehicle calculated during the selection of the MRM strategy.

[0105] The corresponding MRM type may be selected. For example, the MRM strategy determination unit 1330 may determine the straight-line parking 311 because only the straight-line parking 311 is possible in the case where the lateral control function cannot operate normally. For another example, if the driving lane is not detected due to sensor failure and / or external environment, the MRM strategy determination unit 1330 may determine the straight-line parking 311.

[0106] When executing a control operation to stop the vehicle according to the final MRM strategy, the processor 130 may control information indicating that a minimum risk maneuver is being performed to notify another vehicle and / or the driver. The control operation to stop the vehicle may include a driving trajectory generation operation for parking the vehicle and / or a lateral and / or longitudinal control operation following the generated driving trajectory. The processor 130 may control the display 140 to notify the driver that the vehicle is performing a minimum risk maneuver. For another example, the processor 130 may control the communication device 150 to notify another vehicle that the vehicle is performing a minimum risk maneuver. This is just an example for understanding, and the method for notifying the minimum risk operation being performed will not be limited to this.

[0107] The processor 130 may perform a control operation to stop the vehicle according to the determined minimum risk maneuver (MRM) type, and may determine whether the MRC is satisfied. The MRC may mean a stationary state in which the vehicle speed is zero. For example, when the vehicle 100 performs at least one operation according to the determined final MRM type, the processor 130 may determine whether the vehicle 100 enters a stationary state in which the speed of the vehicle 100 is zero. The processor 130 may determine that the MRC is satisfied when the speed of the vehicle 100 is zero.

[0108] If the MRC is satisfied, the processor 130 may terminate the execution of the MRM and switch the automatic driving system (ADS) to a standby mode or an off state. After the automatic driving system (ADS) is switched to a standby mode or an off state, the processor 130 may control so that the vehicle control authority is transferred to the driver (or user).

[0109] The display 140 may intuitively display information related to the vehicle 100. For example, the display 140 may provide the driver of the vehicle 100 with various information related to the state of the vehicle 100 under the control of the processor 130. The various information related to the vehicle state may include information indicating whether at least one of the various components included in the vehicle and / or at least one function of the vehicle is operating normally, and information indicating the driving state of the vehicle. For example, the driving state of the vehicle may include at least one of the following: a state in which the vehicle is autonomously driving, a state in which the vehicle is performing MRM, a state in which MRM has been completed, and a state in which autonomous driving has ended.

[0110] The communication device 150 may communicate with an external device of the vehicle 100. Under the control of the processor 130, the communication device 150 may receive data from outside the vehicle 100 or may transmit data to outside the vehicle 100. For example, the communication device 150 may perform communication by using a wireless communication protocol or a wired communication protocol.

[0111] Although it has been described above Figure 1 Controller 120 and processor 130 are described as separate components in , but controller 120 and processor 130 may be integrated into one component.

[0112] Fig. 9 is a flow chart illustrating the operation of the vehicle. Fig. 9 The vehicle in can be Figure 1 The vehicle 100.

[0113] refer to Fig. 9 , the vehicle 100 can operate the ADS normally in step S910.

[0114] The vehicle 100 may monitor the vehicle state and surrounding environment when performing automatic driving according to the normal operation of the ADS. The vehicle 100 may detect whether a minimum risk maneuver (MRM) is required based on information obtained by monitoring the vehicle state and surrounding environment. If a minimum risk maneuver (MRM) is required, event A1 may occur.

[0115] The vehicle 100 may detect whether the driver's (or user's) intervention is required while performing the automatic driving according to the normal operation of the ADS. If the driver's intervention is required, the vehicle 100 may perform an intervention request (RTI) or issue a warning to the driver through the ADS. The driver's RTI or warning may be event A2. When event A1 occurs during the normal operation of the ADS, the vehicle 100 may proceed to step S920.

[0116] If an A2 event occurs when the ADS is operating normally, the vehicle 100 may determine whether the driver's intervention is detected within a specified time at step S650. If the driver's intervention is not detected within the specified time, the vehicle 100 may determine that event B1 has occurred. If event B1 has occurred, the vehicle 100 may proceed to step S920. If the driver's intervention is detected within the specified time, the vehicle 100 may determine that event B2 has occurred. When event B2 occurs, the vehicle 100 may proceed to step S940.

[0117] The vehicle 100 may perform a minimum risk maneuver (MRM) in step S920. The vehicle 100 may determine the type of MRM based on at least one of vehicle state information and surrounding environment information. The surrounding environment information may include road information and surrounding vehicle information. Figure 3 As shown, the surrounding environment information may include type 1 straight line parking 311, type 2 lane parking 312, type 3 half shoulder parking 313, and / or type 4 full shoulder parking 314. The vehicle 100 may control at least one component in the vehicle to park the vehicle according to the determined MRM type. The vehicle 100 may store supporting data for determining the MRM type in the memory 160.

[0118] The vehicle 100 may determine whether the minimum risk condition is satisfied by causing the speed of the vehicle to become zero by performing the minimum risk maneuver in step S920. If the minimum risk maneuver is satisfied, the vehicle 100 may determine that event C1 has occurred, and may proceed to step S930. The vehicle 100 may determine whether driver intervention is detected during the execution of the minimum risk maneuver. If driver intervention is detected, the vehicle 100 may determine that event C2 has occurred, and may proceed to step S940.

[0119] The vehicle 100 may maintain a state in which the minimum risk condition is satisfied in step S930. The state in which the minimum risk condition is satisfied may mean a state in which the vehicle is parked. For example, the vehicle 100 may maintain a stationary state of the vehicle. For example, regardless of the slope of the road surface at the parking position, the vehicle 100 may perform a control operation to keep the vehicle in a stationary state. The vehicle 100 may determine whether event D1 occurs while maintaining a state in which the minimum risk condition is satisfied. Event D1 may include at least one of: turning off the ADS by the driver and completing the transfer of vehicle control to the driver. If the D1 event occurs, the vehicle 100 may proceed to step S940.

[0120] The vehicle 100 may switch the ADS to a standby mode or an off state in step S940. When the ADS is in the standby or off state, the vehicle 100 does not perform any operation on the automatic driving.

[0121] In the above steps S910 , S920 , S930 , and S950 , the ADS may be in an enabled state, and in step S940 , the ADS may be in a non-enabled state.

[0122] Fig.10 is a flow chart showing a vehicle determining an MRM strategy. Fig.10 The steps can be Fig. 9 Detailed steps of step S920. In the following example, the corresponding steps may be performed sequentially or not. For example, the order of the corresponding steps may be changed, and at least two steps may be performed in parallel. In addition, the following steps may be performed by the processor 130 and / or the controller 120 included in the vehicle 100, or may be implemented by instructions executable by the processor 130 and / or the controller 120.

[0123] refer to Fig.10 , the vehicle 100 may determine whether lateral control is possible based on the vehicle status information in step S1001. For example, the vehicle 100 may monitor the mechanical and / or electrical status of components within the vehicle (e.g., sensors, actuators, etc.), and then may obtain vehicle status information indicating whether mechanical and / or electrical problems occur in the components within the vehicle. Based on the vehicle status information indicating the mechanical and / or electrical status of the sensors and / or actuators, the vehicle 100 may determine whether lateral control (or steering control) of the vehicle 100 is possible.

[0124] If lateral control is not possible, the vehicle 100 may select straight-line parking as the final MRM strategy in step S1021. Figure 3 As shown, since the vehicle 100 that cannot perform lateral control can only perform straight-line parking, the vehicle 100 may determine straight-line parking as the final MRM strategy.

[0125] If lateral control is possible, the vehicle 100 may determine whether there is a road shoulder within the MRC range in step S1003. For example, the vehicle 100 may determine whether there is a road shoulder by checking road information within the MRC range at a specified distance from the vehicle 100. The road information within the MRC range may be obtained through sensing data of a sensor (e.g., the sensor unit 110) provided in the vehicle 100, or may be obtained from map information obtained through the communication device 150.

[0126] If the road shoulder does not exist, the vehicle 100 may determine whether lane detection is possible in step S1015. For example, because the vehicle 100 cannot perform a road shoulder parking strategy when the road shoulder does not exist, the vehicle 100 may check whether lane detection is possible to check whether parking in the lane is possible. The vehicle 100 may determine whether lane detection is possible based on the perception value of the lane detection sensor.

[0127] If lane detection is not feasible (e.g., impossible), the vehicle 100 may select straight parking as the final MRM strategy in step S1021. For example, if lane detection is not feasible (e.g., impossible), the vehicle 100 may determine that in-lane parking cannot be performed and may determine straight parking as the final MRM strategy.

[0128] If lane detection is possible, the vehicle 100 may determine in step 1017 whether the own vehicle is responsible for an accident when parking in the deployment (or execution) lane. For example, the vehicle 100 may calculate the safety distance with the rear vehicle, and may determine the possibility of collision with the rear vehicle and whether there is accident responsibility based on the calculated safety distance. The rear vehicle may refer to a vehicle corresponding to the own vehicle, which is traveling in the same lane. As shown in equation 1, the safety distance with the rear vehicle may include a longitudinal safety distance and a lateral safety distance. If the calculated longitudinal safety distance and lateral safety distance are both negative values, the vehicle 100 may determine that the possibility of collision with the rear vehicle is greater when parking in the deployment lane, and may determine that the own vehicle is responsible for an accident when colliding with the rear vehicle. If at least one of the calculated longitudinal safety distance and lateral safety distance is a positive value, the vehicle 100 may determine that the possibility of collision with the rear vehicle is lower when parking in the deployment lane, and may determine that the own vehicle is not responsible for an accident when a collision with the rear vehicle occurs.

[0129] If it is determined that the own vehicle is responsible for the accident when parking in the deployed lane, the vehicle 100 may proceed to step S1021 and select straight-line parking as the final MRM strategy.

[0130] If it is determined that the own vehicle is not responsible for the accident when in-lane parking is deployed, the vehicle 100 may select in-lane parking as the final MRM strategy in step S1019 .

[0131] If the result of checking step S1003 is that there is a road shoulder, the vehicle 100 may determine whether the size of the shoulder is larger than the vehicle size in step S1005. For example, the vehicle 100 may compare the width of the shoulder with the width of the vehicle and determine whether the vehicle can perform full shoulder parking or half shoulder parking.

[0132] If the size of the shoulder is larger than the size of the vehicle, the vehicle 100 may determine that full shoulder parking can be performed, and may determine in step 1007 whether the own vehicle is responsible for the accident when the full shoulder parking is deployed. For example, the vehicle 100 may calculate a driving path for deploying full shoulder parking, and may calculate a safety distance to at least one nearby vehicle related to the calculated driving path. The at least one nearby vehicle is related to the driving path for deploying full shoulder parking, and may include at least one of a side front vehicle, a side vehicle, and / or a side rear vehicle. Based on the calculated safety distance, the vehicle 100 may determine the possibility of collision with at least one nearby vehicle and whether there is accident responsibility. As shown in Equation 1, the safety distance to at least one nearby vehicle may include a longitudinal safety distance and a lateral safety distance. If the calculated longitudinal safety distance and lateral safety distance are both negative values, the vehicle 100 may determine that the possibility of collision with at least one nearby vehicle when deploying full shoulder parking is high, and may determine that the own vehicle is responsible for the accident when a collision with the corresponding vehicle occurs. If at least one of the calculated longitudinal safety distance and lateral safety distance is a positive value, the vehicle 100 can determine that the possibility of colliding with at least one nearby vehicle when deploying a full shoulder stop is very low, and can determine that the own vehicle is not responsible for the accident when a collision with the corresponding vehicle occurs.

[0133] If it is determined that the own vehicle is not responsible for the accident when full shoulder stopping is deployed, the vehicle 100 may proceed to step S1009 and select full shoulder stopping as the final MRM strategy.

[0134] If it is determined that the own vehicle is responsible for the accident when the full shoulder parking is deployed, the vehicle 100 may proceed to step S1011 and may determine whether the own vehicle is responsible for the accident when the half shoulder parking device is deployed. For example, the vehicle 100 may calculate a driving path for deploying the half shoulder parking and may calculate a safety distance to at least one nearby vehicle related to the calculated driving path. The at least one nearby vehicle is related to the driving path for deploying the half shoulder parking and may include at least one of a side front vehicle, a side vehicle, and / or a side rear vehicle. Based on the calculated safety distance, the vehicle 100 may determine the possibility of collision with at least one nearby vehicle and whether there is an accident responsibility. As shown in Equation 1, the safety distance to at least one nearby vehicle may include a longitudinal safety distance and a lateral safety distance. If the calculated longitudinal safety distance and lateral safety distance are both negative values, the vehicle 100 may determine that the possibility of collision with at least one nearby vehicle is high when deploying the half shoulder parking, and may determine that the own vehicle is responsible for the accident when a collision with the corresponding vehicle occurs. If at least one of the calculated longitudinal safety distance and lateral safety distance is a positive value, the vehicle 100 can determine that the possibility of colliding with at least one nearby vehicle when deploying a half-shoulder stop is very low, and determine that the vehicle itself is not responsible for the accident when a collision with the corresponding vehicle occurs.

[0135] If it is determined that the own vehicle is not responsible for the accident when the half shoulder stop is deployed, the vehicle 100 may proceed to step S1013 and select the half shoulder stop as the final MRM strategy.

[0136] If it is determined that the own vehicle is responsible for the accident when the half-shoulder stop is deployed, the vehicle 100 may execute step S1017.

[0137] As described above, if the vehicle detects a situation during autonomous driving where normal autonomous driving is not feasible (e.g., impossible), the vehicle determines a minimum risk maneuvering strategy based on vehicle status information and / or surrounding environment information, taking into account whether there is accident liability for each minimum risk maneuvering type, thereby minimizing the risk to the vehicle and improving safety.

[0138] Fig.11 is a flow chart illustrating a roadside stop operation during automated driving. Fig.11 The vehicle can be Figure 1 of vehicles 100. Fig.12 An example is shown in which a vehicle meshes a road shoulder area. Fig.13 An example is shown in which a vehicle generates an optimal parking position candidate group. Fig.14 An example of an optimal parking position candidate group is shown. Fig.15 An example is shown in which a vehicle generates an optimal path. Fig.16 and 17 An example is shown in which a vehicle generates an optimal parking position candidate group.

[0139] refer to Fig.11 During the automatic driving of the vehicle 100, the processor 130 may determine whether a minimum risk maneuver is required based on at least one of the surrounding environment information and the vehicle state information of the vehicle 100. If the processor 130 determines that a minimum risk maneuver is required, the processor 130 may determine a minimum risk maneuver type. If the determined minimum risk maneuver type is shoulder parking, the processor 130 may generate an optimal parking position candidate group in step S1110.

[0140] The shoulder parking may be full shoulder parking of MRM type 4, but is not limited thereto. The shoulder parking may be half shoulder parking of MRM type 3.

[0141] In step S1110, if the processor 130 identifies a road shoulder area based on the surrounding environment information generated by the sensor unit 110, the processor 130 may divide the road shoulder area into a plurality of virtual areas. Fig.12 As shown, the processor 130 may grid the shoulder area to a certain size.

[0142] The processor 130 may assign a score to each partitioned virtual area in step S1110. Fig.12 As shown, the processor 130 may calculate a score for each virtual area in consideration of at least one of the current speed of the vehicle, the free space on the shoulder, the distance from the current position of the vehicle to the parking position of the vehicle, and the distance to the obstacle. The processor 130 may assign the highest score to the virtual area with a long parking distance in consideration of the parking distance according to the speed of the vehicle. In order for the vehicle 100 to park, the surrounding space of the virtual area must be wide. Therefore, when there is an obstacle around the virtual area, the processor 130 may assign a low score, and when there is no obstacle, the processor 130 may assign a high score. If there is an obstacle at one position of the virtual area, the processor 130 may assign 0 points.

[0143] refer to Fig.12 , in the case of area 12a, considering the current speed of the vehicle, the stopping distance is relatively long, and the size of the adjacent free space is relatively large. Therefore, 10 points are assigned by the processor 130. In the case of area 12b, area 12b is adjacent to an obstacle (e.g., a wall), and due to the spatial uncertainty reflected by area 12b, area 12b may be assigned a lower score than area 12a. In the case of area 12c, area 12c is the area of ​​obstacle 3, and a score of 0 may be assigned by the processor 130. In the case of area 12d, the stopping distance is insufficient when considering the current speed of the vehicle, so a lower score than area 12a may be assigned.

[0144] refer to Fig.13 , the processor 130 may match the virtual window area W corresponding to the vehicle size with the plurality of virtual areas, and may generate parking position candidate groups X1 and X2 based on a value obtained by summing the scores of the respective virtual areas included in the virtual window area W. The processor 130 may replace the virtual window area W with each virtual area (grid), and may generate high-order N parking position candidate groups based on a value obtained by summing the scores of the respective virtual areas included in the virtual window area W.

[0145] After generating the parking position candidate group, the processor 130 may generate a path from the current position of the vehicle 100 to each of the parking position candidate group in step S1120 .

[0146] In step S1130, the processor 130 may select the final parking position by taking into account at least one of: a travel distance of a path of each parking position candidate group, a parking characteristic of the vehicle when parking following the path of each parking position candidate group, and a value obtained by adding scores of respective virtual areas of an area occupied by the vehicle when parking following the path of each parking position candidate group.

[0147] The processor 130 may calculate the driving distance of the path to each parking location candidate group, and may assign a lower score as the distance increases. Fig.15 , because path 15a is greater than path 15b, processor 130 may assign a lower score to path 15a than to path 15b.

[0148] The processor 130 may generate a first selection score for each driving distance of the path to each parking position candidate group based on the pre-stored map data. For example, the processor 130 may generate a first selection score for each driving distance of the path to each parking position candidate group by using the map data that outputs the score according to the driving distance.

[0149] The processor 130 may follow the path to each parking position candidate group, and may calculate the parking characteristics (e.g., parking direction associated with the driving direction) of the vehicle 100 when parking (e.g., parallel parking, angled parking, etc.). The processor 130 may calculate the parking characteristics of the vehicle 100 based on the angle between the parking characteristics of the vehicle 100 and the driving direction when the vehicle 100 is parked. If the direction of the vehicle 100 when the vehicle 100 is parked is closer to the driving direction (the angle between the parking characteristics of the vehicle 100 when the vehicle 100 is parked and the driving direction is smaller), which may be a preferred parking characteristic, the processor 130 may give a higher score.

[0150] For example, in Fig.15In the example, in the case of path 15a, the parking characteristic of the vehicle 100 when parking is parallel to the driving direction, while in the case of path 15b, the parking characteristic of the vehicle 100 when parking is perpendicular to the driving direction (in the case of path 15b, the parking characteristic of the vehicle 100 when parking is at a smaller angle to the driving direction). Therefore, the processor 130 may assign a higher score to path 15a than to path 15b.

[0151] The processor 130 may generate a second selection score for each parking characteristic of the vehicle 100 when parking by following a path to each parking position candidate group based on pre-stored map data. For example, the processor 130 may generate a second selection score for each parking characteristic of the vehicle 100 when parking by using map data that outputs a score based on an angle between a driving direction of the vehicle 100 and the parking characteristic of the vehicle 100 when parking.

[0152] The processor 130 may generate a third selection score obtained by adding the scores of the respective virtual areas of the area occupied by the vehicle when parking by following the path to each parking position candidate group. Fig.15 , the processor 130 may generate the third selection score by summing the scores of the virtual areas included in the parking position candidate group X1. The processor 130 may generate the third selection score by summing the scores of the virtual areas included in the parking position candidate group X2.

[0153] The processor 130 may sum the first selection score, the second selection score, and the third selection score, and may select a parking position candidate group with the highest sum value among the corresponding parking position candidate groups as the final parking position. The processor 130 may use the path to the final parking position as the path actually followed.

[0154] For example, in Fig.15 , if the value obtained by summing the first selection score, the second selection score, and the third selection score of the parking position candidate group X1 (or summing the first selection score, the second selection score, and the third selection score with different weights) is 8.7, and if the value obtained by summing the first selection score, the second selection score, and the third selection score of the parking position candidate group X2 (or the weighted sum) is 6.5, the processor 130 may select the parking position candidate group X1 as the final parking position. The processor 130 may use the path 15a to the parking position candidate group X1 as the path actually followed.

[0155] The processor 130 may send a path following control command for the final parking position to the controller 120 in step S1140. For example, after selecting the parking position candidate group X1 as the final parking position, the processor 130 may send the following control command to the controller 120: follow the path 15a for the parking position candidate group X1.

[0156] In step S1150, the processor 130 may determine whether the vehicle 100 has reached the final parking position. When the vehicle 100 follows the path to reach the final parking position, a situation may occur in which the final parking position in which the vehicle intends to park disappears due to a certain situation (for example, another vehicle that has been parked at the final parking position moves). Therefore, even during the path following control, it may be necessary to generate a parking position candidate group in real time and change the parking position when necessary. However, if the scores of the parking position candidates are similar, the parking position may be frequently changed. Therefore, only when the score is not the same as the score of the previously generated parking position candidate group, the optimal path is generated and the parking position selection operation is performed.

[0157] If the processor 130 determines that the vehicle 100 has not reached the final parking position in step S1160, the processor 130 may generate a parking position candidate group for changing the parking position. As an embodiment, if the vehicle 100 has not reached the final parking position within a preset time, the processor 130 may determine that the vehicle has not reached the final parking position.

[0158] In step S1170, if the parking position candidate group generated in step S1160 is not the same as the optimal parking position candidate group generated in step S1110 (excluding the final parking position generated in step S1130), the processor 130 may perform optimal path generation (S1120), parking position selection (S1130), and path following control (S1140).

[0159] In step S1170 , if the parking position candidate group generated in step S1160 is the same as the optimal parking position candidate group generated in step S1110 (excluding the final parking position generated in step S1130 ), the processor 130 may perform the path following control ( S1140 ).

[0160] If the processor 130 determines that the vehicle 100 has failed to reach the final parking position, the processor 130 may generate a parking position candidate group different from the previously generated best parking position candidate group. If the scores of the parking position candidates are similar, the parking position may be frequently changed. Therefore, the processor may generate a parking position candidate group different from the previously generated best parking position candidate group, and may perform steps S1120, S1130, and S1140.

[0161] In step S1110, there are not only a plurality of spaces separated by obstacles 3, etc., but also Fig.16 When the wide space is shown, the processor 130 may generate a set of optimal parking position candidates.

[0162] In step S1110, the processor 130 may not only divide (mesh) the Fig.17 The outer area of ​​lane 5 (relative to the right area of ​​lane 5) shown, and a part of the inner area of ​​lane 5 (relative to the left area of ​​lane 5) can also be divided (gridified) into multiple virtual areas. This grid expansion can be applied to areas where parking is not allowed (for example, white solid line areas).

[0163] If the processor 130 identifies the shoulder area and the lane based on the surrounding environment information generated by the sensor unit 110 in step S1110 and determines that the type of the corresponding lane is a lane where parking is allowed, the processor 130 may even divide a portion of the inner area of ​​the lane into a plurality of virtual areas.

[0164] According to one or more aspects described herein, an autonomous vehicle may include: at least one sensor configured to detect the surroundings of the vehicle and generate surrounding information; a processor configured to monitor the state of the vehicle and generate vehicle state information, and determine whether a minimum risk maneuver is required based on at least one of the surrounding information and the vehicle state information during autonomous driving of the vehicle; and a controller configured to control the operation of the vehicle under the control of the processor. When the processor determines that a minimum risk maneuver is required, the processor determines a minimum risk maneuver type, and when the determined minimum risk maneuver type is shoulder parking, the processor generates a parking position candidate group.

[0165] If the processor identifies a shoulder area based on the surrounding environment information, the processor may divide the shoulder area into a plurality of virtual areas. The processor may calculate a score for each virtual area in consideration of at least one of a current speed of the vehicle, a free space on the shoulder, and a distance from a current position of the vehicle to a parking position of the vehicle. The processor may generate a parking position candidate group based on the calculated score of each virtual area.

[0166] The processor may assign a score of 0 to an area where an obstacle exists among the plurality of virtual areas.

[0167] The processor may match a virtual window area corresponding to the vehicle size with the plurality of virtual areas, and may generate the parking position candidate group according to a value obtained by summing scores of respective virtual areas included in the virtual window area.

[0168] After generating at least one parking position candidate group, the processor may generate a path from the current position of the vehicle to each parking position candidate of the at least one parking position candidate group.

[0169] The processor may select the final parking position based on at least one of a travel distance of a path from the current position to each parking position candidate, a parking characteristic of the vehicle after following a path from the current position to each parking position candidate, or a value obtained by adding scores of a virtual area of ​​an area occupied by the vehicle after following a path from the current position to each parking position candidate.

[0170] The processor may generate a first selection score for each driving distance of a path to each parking location candidate group based on pre-stored map data.

[0171] The processor may generate a second selection score for each parking characteristic of the vehicle when parking following a path to each parking location candidate group based on pre-stored map data.

[0172] The processor may sum the first selection score, the second selection score, and a third selection score obtained by adding scores of respective virtual areas of the vehicle occupancy area when parking following a path to each parking position candidate group, and may select a parking position candidate group with a highest sum value among the corresponding parking position candidate groups as a final parking position.

[0173] The processor may send a path following control command to the controller for the final parking position.

[0174] If the processor determines that the vehicle fails to reach the final parking position within a preset time, the processor may generate a parking position candidate group for changing the parking position.

[0175] According to one or more aspects described herein, an operation method of an autonomous vehicle is provided. The operation method may include: detecting the vehicle surroundings during the autonomous driving of the vehicle and generating vehicle surroundings information; monitoring the vehicle state during the autonomous driving of the vehicle and generating vehicle state information; during the autonomous driving of the vehicle, determining whether a minimum risk maneuver is required based on at least one of the surroundings information and the vehicle state information; when it is determined that a minimum risk maneuver is required, determining a minimum risk maneuver type, and when the determined minimum risk maneuver type is shoulder parking, generating a parking position candidate group.

[0176] Generating a parking position candidate group may include: when identifying a shoulder area based on surrounding environment information, dividing the shoulder area into a plurality of virtual areas; calculating a score for each of the virtual areas taking into account at least one of a current speed of the vehicle, free space on the shoulder, and a distance from a current position of the vehicle to a parking position of the vehicle; and generating a parking position candidate group based on the calculated score of each virtual area.

[0177] Generating the parking position candidate group according to the calculated score of each virtual area may include matching a virtual window area corresponding to the vehicle size with a plurality of virtual areas, and generating the parking position candidate group based on a value obtained by summing the scores of the respective virtual areas included in the virtual window area.

[0178] The operating method may further include generating a path from a current position of the vehicle to each parking position candidate of at least one parking position candidate group after generating the parking position candidate group.

[0179] The operating method may further include, after generating a path from the current position of the vehicle to each parking position candidate of the at least one parking position candidate group, selecting a final parking position based on at least one of: a travel distance of the path from the current position to each parking position candidate, a parking characteristic of the vehicle after following the path from the current position to each parking position candidate, or a score of each of a virtual area of ​​an area occupied by the vehicle after following the path from the current position to each parking position candidate.

[0180] Selecting the final parking position may include: generating a first selection score for each travel distance of a path to each parking position candidate group based on pre-stored map data; generating a second selection score for each parking characteristic of the vehicle when parking by following the path to each parking position candidate group according to the pre-stored map data; and generating a third selection score by adding scores of respective virtual areas of an area occupied by the vehicle when parking by following the path to each parking position candidate group.

[0181] The operation method may further include, after generating the third selection score: summing the first selection score, the second selection score, and the third selection score; and selecting a parking position candidate group having a highest value obtained by summing the first selection score, the second selection score, and the third selection score in the corresponding parking position candidate group as the final parking position.

[0182] The operating method may further include, after selecting the final parking position, controlling the vehicle to follow a path to the final parking position.

[0183] The operating method may further include, after controlling the vehicle to follow the path to the final parking position, generating a parking position candidate group for changing the parking position when it is determined that the vehicle fails to reach the final parking position within a preset time.

[0184] According to one or more aspects of the present invention, if shoulder parking is required as a minimum risk maneuvering strategy during vehicle autonomous driving, the optimal parking position can be obtained under various conditions (such as obstacles, narrow shoulder space, many spaces available for vehicle parking, etc.).

[0185] As described above, if the vehicle needs to use shoulder parking as the maneuver strategy with the least risk when autonomously driving, the vehicle can obtain the best parking position in various situations (such as obstacles, narrow shoulder space, many available spaces for parking the vehicle, etc.).

[0186] Although examples are described above, the features and / or steps of these examples may be combined, divided, omitted, rearranged, modified, and / or increased in any desired manner. Various variations, modifications, and improvements will readily occur to those skilled in the art. Such variations, modifications, and improvements are intended to be a part of this specification—but not expressly described in this specification—and are within the spirit and scope of the specification described herein. Therefore, the foregoing description is intended to be exemplary only and not limiting.

Claims

1. An autonomous driving vehicle, comprising: at least one sensor configured to: detect the surrounding environment of the vehicle and generate surrounding environment information; a processor configured to: generate vehicle state information by monitoring a state of the vehicle during autonomous driving of the vehicle, and determine whether a minimum risk maneuver (MRM) is required based on at least one of the surrounding environment information and the vehicle state information; as well as a controller configured to: control the operation of the vehicle under the control of the processor, Wherein, based on determining that the MRM is needed, the processor is configured to determine an MRM type, and when the determined MRM type is shoulder parking, the processor is configured to generate at least one parking position candidate group.

2. The vehicle according to claim 1, wherein: The processor is configured to: identifying a road shoulder area based on the surrounding environment information, Dividing the road shoulder area into a plurality of virtual areas; determining a score for each virtual area, wherein the score is determined based on at least one of the following conditions: a speed of the vehicle, a free space on the shoulder area, and a distance from a current position of the vehicle to a parking position of the vehicle, and The at least one parking position candidate group is generated based on the determined score of each virtual area.

3. The vehicle according to claim 2, wherein: The processor is configured to assign a predetermined score to a virtual area including an obstacle among the plurality of virtual areas.

4. The vehicle according to claim 2, wherein: The processor is configured to: matching a virtual window area corresponding to the size of the vehicle with the plurality of virtual areas; and The at least one parking position candidate group is generated based on a value obtained by summing scores of respective virtual areas included in the virtual window area.

5. The vehicle according to claim 1, wherein: The processor is configured to: After generating the at least one parking position candidate group, a path from the current position of the vehicle to each parking position candidate of the at least one parking position candidate group is generated.

6. The vehicle according to claim 5, wherein: The processor is configured to: The final parking location is selected based on at least one of the following: the travel distance from the current position to each parking position candidate, the parking characteristics of the vehicle after following the path from the current position to each parking position candidate, and a value obtained by adding scores of a virtual area of ​​the vehicle occupation area after following the path from the current position to each parking position candidate.

7. The vehicle according to claim 6, wherein: The processor is configured to generate a first selection score based on each travel distance of a path from the current location to a corresponding parking location candidate based on stored map data.

8. The vehicle according to claim 7, wherein: The processor is configured to generate, based on the stored map data, a second selection score for each parking characteristic of the vehicle after following a path from the current location to a corresponding parking location candidate.

9. The vehicle according to claim 8, wherein: The processor is configured to: generating a final score for a corresponding parking position candidate based on the first selection score, the second selection score, and a third selection score obtained by adding scores of respective virtual areas of the vehicle occupancy area after following a path from the current position to the corresponding parking position candidate, and A parking position candidate with a highest final score among the final scores of the corresponding parking position candidates is selected as the final parking position.

10. The vehicle according to claim 6, wherein: The processor is configured to send a path following control command to the controller for the final parking position.

11. The vehicle according to claim 10, wherein: The processor is configured to generate a parking position candidate group for changing the parking position based on determining that the vehicle fails to reach the final parking position within a preset time.

12. A method for operating an autonomous driving vehicle, the method comprising: During autonomous driving of the vehicle: Generate surrounding environment information by detecting the surrounding environment of the vehicle; generating vehicle status information by monitoring the status of the vehicle; determining whether a minimum risk maneuver (MRM) is required based on at least one of the surrounding environment information and the vehicle state information; as well as An MRM type is determined based on the determination that the MRM is required, and when the determined MRM type is shoulder parking, at least one parking position candidate group is generated.

13. The operating method according to claim 12, wherein: Generating the at least one parking position candidate group comprises: Based on the road shoulder area identified from the surrounding environment information, dividing the road shoulder area into a plurality of virtual areas; determining a score for each virtual area, wherein the score is determined based on at least one of the following conditions: a speed of the vehicle, a free space on the shoulder area, and a distance from a current position of the vehicle to a parking position of the vehicle, and Based on the determined score of each virtual area, the at least one parking position candidate group is generated.

14. The operating method according to claim 13, wherein: Generating the at least one parking position candidate group comprises: matching a virtual window area corresponding to the size of the vehicle with the plurality of virtual areas; The at least one parking position candidate group is generated based on a value obtained by summing scores of the respective virtual areas included in the virtual window area.

15. The operating method according to claim 12, further comprising: After generating the at least one parking position candidate group, a path from the current position of the vehicle to each parking position candidate of the at least one parking position candidate group is generated.

16. The operating method according to claim 15, further comprising: After generating a path from the current position of the vehicle to each parking position candidate of the at least one parking position candidate group, a final parking position is selected based on at least one of a travel distance of the path from the current position to each parking position candidate, a parking characteristic of the vehicle after following the path from the current position to each parking position candidate, and a score of each virtual area of ​​the vehicle occupation area after following the path from the current position to each parking position candidate.

17. The operating method according to claim 16, wherein: Selecting the final parking position includes: generating, based on the stored map data, a first selection score for each travel distance of a path from the current position to a corresponding parking location candidate; generating, based on the stored map data, a second selection score for each parking characteristic of the vehicle after following a path from the current position to a corresponding parking position candidate; and A third selection score is generated by adding scores of respective virtual areas of the vehicle occupancy area following from the current position to the corresponding parking position candidate.

18. The operating method according to claim 17, further comprising: After generating the third selection score: generating a final score for a corresponding parking location candidate based on the first selection score, the second selection score, and the third selection score; as well as Among the final scores of the corresponding parking position candidates, a parking position candidate with the highest final score is selected as the final parking position.

19. The operating method according to claim 16, further comprising: After selecting the final parking position, the vehicle is controlled to follow a path to the final parking position.

20. The operating method according to claim 19, further comprising: After controlling the vehicle to follow the path to the final parking position, a parking position candidate group for changing the parking position is generated based on determining that the vehicle fails to reach the final parking position within a preset time.

Images