Vehicle for performing minimal risk motor and method of operating a vehicle

Abstract

Various embodiments of the present invention relate to a vehicle and a method of operation of the vehicle for performing minimum risk maneuvers. The autonomous vehicle may detect whether a minimum risk maneuver is required based on at least one of ambient information and vehicle state information during autonomous driving of the vehicle, determine a minimum risk maneuver type and a target point at which the vehicle will stop when the minimum risk maneuver is required, and controlling the vehicle to stop at the target point based on the determined minimum risk maneuver type and the target point.

Description

Technical Field

[0001] This document relates to a vehicle for performing a minimum risk maneuver and a method of operating the vehicle. Background Art

[0002] Recently, advanced driver assistance systems (ADAS) have been developed to assist the driver in driving. ADAS has multiple sub-technical categories and provides convenience to the driver. This ADAS is also known as autonomous driving or automated driving system (ADS).

[0003] Meanwhile, an error may occur in the autonomous driving system when the vehicle performs autonomous driving. If an appropriate response is not taken to such an abnormality in the autonomous driving system, the vehicle may be placed in a dangerous state. Summary of the invention

[0004] Therefore, various embodiments of this document disclose a vehicle that performs a minimum risk maneuver (MRM) to eliminate (or reduce) risk when a situation in which normal autonomous driving is not possible is detected during autonomous driving, and a method of operating the vehicle.

[0005] Various embodiments of this document disclose a method and apparatus for determining a minimum risk maneuver parking type and parking location when a situation that does not allow normal autonomous driving is detected in a vehicle during autonomous driving.

[0006] Various embodiments of this document disclose a method and apparatus for determining a minimum risk maneuver parking type and parking location based on route complexity and parking risk when a situation in which normal autonomous driving is not possible is detected in a vehicle during autonomous driving.

[0007] The technical problems to be solved in this document are not limited to the above-mentioned technical problems, and other unmentioned technical problems can be clearly understood by those skilled in the art from the following description.

[0008] According to various embodiments of this document, an autonomous vehicle includes: at least one sensor for detecting the surrounding environment of the vehicle and generating surrounding environment information; a processor for generating vehicle state information by monitoring the state of the vehicle and controlling autonomous driving of the vehicle; and a controller for controlling the operation of the vehicle according to the control of the processor.

[0009] According to one embodiment, the processor can determine whether a minimum risk maneuver is required based on at least one of surrounding environment information and vehicle status information during autonomous driving of the vehicle, determine the minimum risk maneuver type and the target point at which the vehicle will stop when a minimum risk maneuver is required, and control the vehicle to stop at the target point based on the determined minimum risk maneuver type and target point.

[0010] According to one embodiment, the processor may calculate the maximum distance or maximum time that can be traveled in a minimum risk maneuvering state, search for a parking area that can be reached within the maximum distance or maximum time, classify the searched parking areas into full-shoulder parking areas and half-shoulder parking areas, calculate at least one of the route complexity and parking risk of each full-shoulder parking area, determine whether it is possible to park in the full-shoulder parking area based on the calculated route complexity and at least one of the parking risks, and when parking is not possible in all full-shoulder parking areas, calculate at least one of the route complexity and parking risk of each half-shoulder parking area, and determine the minimum risk maneuvering type and the target point where the vehicle will stop based on at least one of the route complexity and parking risk of the half-shoulder parking area.

[0011] According to one embodiment, the processor can calculate the maximum distance or maximum time that can be traveled in a minimum risk maneuvering state, search for a parking area that can be reached within the maximum distance or maximum time, calculate at least one of the route complexity and parking risk at the parking area, and determine the minimum risk maneuvering type and the target point where the vehicle will stop based on the route complexity and parking risk of each parking area.

[0012] According to one embodiment, the processor may search for an all-shoulder parking area that can be reached within a maximum distance or a maximum time, calculate the route complexity of each all-shoulder parking area searched, determine the all-shoulder parking area with a route complexity lower than or equal to a preset value and the lowest route complexity value as the target point where the vehicle will stop, and determine the all-shoulder parking as the minimum risk maneuver type.

[0013] According to one embodiment, when there is no full-shoulder parking area with a route complexity lower than or equal to a preset value, the processor may search for a half-shoulder parking area; when there is a half-shoulder parking area with a route complexity lower than that of the full-shoulder parking area and a parking risk lower than a preset risk, the half-shoulder parking area with the lowest parking risk is determined as the target point where the vehicle will stop, and half-shoulder parking is determined as the minimum risk maneuvering type; and when there is no half-shoulder parking area with a route complexity lower than that of the full-shoulder parking area, parking in the lane or parking in a straight line is determined as the minimum risk maneuvering type.

[0014] According to one embodiment, when there is no full-shoulder parking area with a route complexity lower than or equal to a preset value, the processor may search for a half-shoulder parking area, and when there is a half-shoulder parking area with a route complexity lower than or equal to a preset value and a parking risk lower than the preset risk, the half-shoulder parking area with the lowest parking risk is determined as the target point where the vehicle will stop, and half-shoulder parking is determined as the minimum risk maneuvering type; and when there is no half-shoulder parking area with a route complexity less than or equal to the preset value, parking in the lane or parking in a straight line is determined as the minimum risk maneuvering type.

[0015] According to one embodiment, the processor may search for full-shoulder parking areas and half-shoulder parking areas that can be reached within a maximum distance or a maximum time, calculate the route complexity and parking risk of each of the searched full-shoulder parking areas and half-shoulder parking areas, and when there is no parking area whose parking risk is less than a preset risk and whose route complexity is lower than or equal to a preset value, select in-lane parking or straight-line parking as the minimum risk maneuver type.

[0016] According to one embodiment, the processor may, when there is a parking area with a parking risk less than a preset risk and a route complexity less than or equal to a preset value, select a parking area with the lowest route complexity among the parking areas with a parking risk less than a preset risk; when the selected parking area is a full-shoulder parking area, determine full-shoulder parking as the minimum risk maneuvering type, and determine the selected parking area as a target point; and when the selected parking area is not a full-shoulder parking area, determine half-shoulder parking as the minimum risk maneuvering type, and determine the selected parking area as the target point.

[0017] According to one embodiment, the processor may calculate the route complexity based on the number of intersections to be passed, the number of left turns, the number of right turns, and the distance to the destination.

[0018] According to one embodiment, the processor may calculate the parking risk based on the size of the parking area, whether the area is a no-parking area, maximum speed information of the road, and traffic flow information.

[0019] According to various embodiments of the present document, a method for operating a vehicle may include: during autonomous driving of the vehicle, obtaining at least one of surrounding environment information and vehicle status information; determining whether a minimum risk maneuver is required based on the at least one of the surrounding environment information and the vehicle status information; when it is determined that a minimum risk maneuver is required, determining a minimum risk maneuver type and a target point at which the vehicle will stop; and controlling the vehicle to stop at the target point based on the determined minimum risk maneuver type and target point.

[0020] According to one embodiment, determining the minimum risk maneuvering type and the target point may include: calculating the maximum distance or maximum time that can be traveled under the minimum risk maneuvering state; searching for a parking area that can be reached within the maximum distance or maximum time; classifying the searched parking areas into full-shoulder parking areas and half-shoulder parking areas; calculating at least one of the route complexity and parking risk at the full-shoulder parking area; determining whether parking is possible in the full-shoulder parking area based on at least one of the calculated route complexity and parking risk; and when parking is not possible in the full-shoulder parking area, calculating at least one of the route complexity and parking risk at the half-shoulder parking area, and determining the minimum risk maneuvering type and the target point where the vehicle will stop based on at least one of the route complexity and parking risk at the half-shoulder parking area.

[0021] According to one embodiment, determining the minimum risk maneuvering type and the target point may also include: calculating the maximum distance or maximum time that can be traveled under the minimum risk maneuvering state; searching for parking areas that can be reached within the maximum distance or maximum time, and calculating at least one of the route complexity and parking risk of each parking area; and determining the minimum risk maneuvering type and the target point where the vehicle will stop based on the route complexity and the parking risk of the parking area.

[0022] According to one embodiment, determining the minimum risk maneuver type and target point may also include: searching for an all-shoulder parking area that can be reached within a maximum distance or a maximum time; calculating the route complexity of the searched all-shoulder parking area; determining the all-shoulder parking area with a route complexity lower than or equal to a preset value and the lowest route complexity value as the target point where the vehicle is to stop; and determining all-shoulder parking as the minimum risk maneuver type.

[0023] According to one embodiment, determining the minimum risk maneuvering type and target point may also include: when there is no full-shoulder parking area with a route complexity less than or equal to a preset value, searching for a half-shoulder parking area; when there is a half-shoulder parking area with a route complexity lower than that of the full-shoulder parking area and a parking risk lower than a preset risk, determining the half-shoulder parking area with the lowest parking risk as the target point where the vehicle will stop, and determining half-shoulder parking as the minimum risk maneuvering type; and when there is no half-shoulder parking area with a route complexity lower than that of the full-shoulder parking area, determining parking in the lane or parking in a straight line as the minimum risk maneuvering type.

[0024] According to one embodiment, determining the minimum risk maneuvering type and target point may also include: when there is no full-shoulder parking area with a route complexity less than or equal to a preset value, searching for a half-shoulder parking area; when there is a half-shoulder parking area with a route complexity lower than or equal to a preset value and a parking risk lower than the preset risk, determining the half-shoulder parking area with the lowest parking risk as the target point where the vehicle will stop, and determining half-shoulder parking as the minimum risk maneuvering type; and when there is no half-shoulder parking area with a route complexity lower than or equal to the preset value, determining parking in the lane or parking in a straight line as the minimum risk maneuvering type.

[0025] According to one embodiment, determining the minimum risk maneuvering type and target point may include: searching for full-shoulder parking areas and half-shoulder parking areas that can be reached within a maximum distance or a maximum time; calculating the route complexity and parking risk of the searched full-shoulder parking areas and half-shoulder parking areas; and when there is no parking area with a parking risk less than a preset risk and a route complexity lower than or equal to a preset value, selecting in-lane parking or straight-line parking as the minimum risk maneuvering type.

[0026] Preferably, determining the minimum risk maneuvering type and the target point also includes: when there is a parking area with a parking risk less than a preset risk and a route complexity less than or equal to a preset value, selecting a parking area with the lowest route complexity among the parking areas with a parking risk less than the preset risk; when the selected parking area is a full-shoulder parking area, determining full-shoulder parking as the minimum risk maneuvering type, and determining the selected parking area as the target point; and when the selected parking area is not a full-shoulder parking area, determining half-shoulder parking as the minimum risk maneuvering type, and determining the selected parking area as the target point.

[0027] According to one embodiment, the route complexity may be calculated based on the number of intersections to be passed, the number of left turns, the number of right turns, and the distance to the destination.

[0028] According to one embodiment, the parking risk may be calculated based on the size of the parking area, whether the area is a no-parking area, maximum speed information of the road, and traffic flow information. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a block diagram illustrating a vehicle according to various embodiments of this document.

[0030] Figure 2 is a functional block diagram illustrating a processor according to various implementations of this document.

[0031] Figure 3is a diagram illustrating a minimum risk maneuver (MRM) strategy for each vehicle state according to various embodiments of this document.

[0032] Figure 4 is a flow chart illustrating operations for performing a minimal risk maneuver of a vehicle, according to various implementations.

[0033] Figure 5 is a flow chart illustrating operations for determining a target point and MRM type considering route complexity and parking risk when performing a minimum risk maneuver of a vehicle according to various embodiments.

[0034] Figure 6 is a diagram illustrating an example of calculating a maximum time that can be traveled in a fault state according to various embodiments.

[0035] Figure 7 is shown for explanation Figure 5 A diagram of an example of the operation of .

[0036] Figure 8 is a flow chart illustrating operations for determining a target point and an MRM type taking into account route complexity and parking risk when performing a minimum risk maneuver of a vehicle according to other embodiments. DETAILED DESCRIPTION

[0037] Hereinafter, embodiments of the present document will be described in detail with reference to the accompanying drawings.

[0038] The configuration of this document and the operational effects according to it will be clearly understood through the following detailed description. Before the detailed description of this document, although the same components are shown in different drawings, the same components are indicated by the same symbols as much as possible, and it should be noted that when it is determined that a known configuration may make the subject matter of the present disclosure unclear, its detailed description will be omitted.

[0039] Prior to the detailed description of this document, the terms used in this document can be defined as follows.

[0040] The vehicle is provided with an automated driving system (ADS) and is capable of autonomous driving. For example, the vehicle can perform at least one of steering, acceleration, deceleration, lane change, and stopping (or stopping) through the ADS without driver operation. The ADS may include, for example, at least one of a pedestrian detection and collision mitigation system (PDCMS), a lane change decision assistance system (LCDAS), a lane departure warning system (LDWS), an adaptive cruise control (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), and a low speed follow (LSF).

[0041] The driver is the person who uses the vehicle and is provided with the service of the autonomous driving system.

[0042] The vehicle control authority is the authority to 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, at least one of 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 powertrain control function, a safety zone detection function, an engine on / off function, a power on / off function, and a vehicle lock / unlock. The listed vehicle functions are merely examples to aid understanding, and the implementation of this document is not limited thereto.

[0043] The shoulder may refer to the space between the outermost road boundary (or outermost lane boundary) and the edge of the road (eg, curb, guardrail) in the direction of vehicle travel.

[0044] Figure 1 is a block diagram illustrating a vehicle according to various embodiments of this document.

[0045] Figure 1 The configuration of the vehicle shown in is an example, and each component may be configured by a chip, a component, or an electronic circuit, or may be configured by a combination of chips, components, and / or electronic circuits. According to one embodiment, Figure 1 Some components shown in the figure may be divided into multiple components and configured as different chips, different components, or different electronic circuits, and some components may be combined to be configured as one chip, one component, or one electronic circuit. According to one embodiment, the Figure 1 Some components shown in the figure may be changed, or other components not shown may be added.

[0046] Figure 2 is a functional block diagram illustrating a processor according to various embodiments of this document, Figure 3 is a diagram illustrating a minimum risk maneuver (MRM) strategy for each vehicle state according to various embodiments of this document.

[0047] Reference Figure 1 , the vehicle 100 may include a sensor unit 110 , a controller 120 , a processor 130 , a display 140 , a communication device 150 , and a memory 160 .

[0048] According to various embodiments, the sensor unit 110 may sense the environment around the vehicle 100 using at least one sensor, and generate data related to the surrounding environment based on the sensing results. According to one embodiment, the sensor unit 110 may obtain road information, information about objects around the vehicle (e.g., other vehicles, people, objects, curbs, guardrails, lanes, obstacles), and / or position information of the vehicle based on the sensing data obtained from at least one sensor. The road information may include, for example, at least one of the position of the lane, the shape of the lane, the color of the lane, the type of the lane, the number of lanes, the presence of a shoulder, and the size of the shoulder. The objects around the vehicle may include, for example, at least one of the position of the object, the size of the object, the shape of the object, the distance to the object, and the relative speed relative to the object.

[0049] According to one embodiment, the sensor unit 110 may include at least one of 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 only examples to help understanding, and the sensors included in the sensor unit 110 of this document are not limited thereto. The camera may capture images around the vehicle and generate image data including lanes and / or surrounding objects on the front side, rear side, and / or lateral side of the vehicle 100. The LiDAR may use light (or laser) to generate information about objects located at the front side, rear side, and / or lateral side of the vehicle 100. The radar may use electromagnetic waves (or radio waves) to generate information about objects located at the front side, rear side, and / or lateral side of the vehicle 100. The ultrasonic sensor may use ultrasonic waves to generate information about objects located at the front side, rear side, and / or lateral side of the vehicle 100. The infrared sensor may use infrared rays to generate information about objects located at the front side, rear side, and / or lateral side of the vehicle 100. 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 position data of the vehicle based on a signal generated by at least one of the GPS sensor, the DGPS sensor, and the GNSS sensor.

[0050] According to various embodiments, 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, a power on / off, and a vehicle lock / unlock.

[0051] According to an embodiment, the controller 120 may control the operation of at least one component of the vehicle for autonomous driving and / or at least one function of the vehicle and / or a minimum risk maneuver (MRM) of the vehicle 100 under the control of the processor 130. For example, the controller 120 may control at least one operation of 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 powertrain control function, and a safety area detection function for a minimum risk maneuver.

[0052] According to various embodiments, the processor 130 may control the overall operation of the vehicle 100. According to one embodiment, the processor 130 may include an electric control unit (ECU) capable of controlling components inside the vehicle 100 in an integrated manner. For example, the processor 130 may include a central processing unit (CPU) or a microcontroller unit (MCU) capable of performing operation processing.

[0053] According to various embodiments, when a specified event occurs, the processor 130 may activate an automated driving system (ADS) to control components within the vehicle 100 so that the vehicle can perform autonomous driving. The specified event may occur when autonomous driving of the vehicle is requested, when vehicle control authority is delegated from the driver, or when conditions specified by the driver and / or a designer are met.

[0054] According to various embodiments, the processor 130 may determine whether normal autonomous driving is possible based on at least one of vehicle state information and surrounding environment information during autonomous driving. When normal autonomous driving is not possible, the processor 130 may determine an MRM strategy and control the vehicle to stop according to the determined MRM strategy. Here, the MRM strategy may be a strategy for stopping the vehicle at a parking position determined according to the determined MRM type.

[0055] According to one embodiment, the processor 130 may include a vehicle state information acquisition unit 210, a surrounding environment information acquisition unit 220, and an MRM strategy determination unit 240. Figure 2 as shown in .

[0056] The vehicle status information acquisition unit 210 may acquire vehicle status information indicating whether mechanical and / or electrical defects occur in components inside the vehicle by monitoring the mechanical and / or electrical states of components inside the vehicle (e.g., sensors, actuators, etc.) from the time point when the ADS is activated. The vehicle status information may include information about the mechanical and / or electrical states of components inside the vehicle. For example, the vehicle status information may include information indicating whether functions required for autonomous driving can operate normally according to the mechanical and / or electrical states of components inside the vehicle.

[0057] The surrounding environment information acquisition unit 220 may acquire the environment information around the vehicle from the time point when the ADS is activated using the sensor unit 110 and / or the communication device 150. The surrounding environment information acquisition unit 220 may include: a road information acquisition unit 221 for acquiring information about the road on which the vehicle is traveling and surrounding roads; and a surrounding object information acquisition unit 223 for detecting objects around the vehicle from the sensor unit 110.

[0058] According to one embodiment, the road information acquisition unit 221 may acquire road information around the location where the vehicle is traveling through the sensor unit 110. According to one embodiment, the road information acquisition unit 221 may acquire road information around the location where the vehicle is traveling based on map information acquired from an external device (e.g., another vehicle, or a server) through the communication device 150 or the vehicle's built-in map information and location information.

[0059] According to one embodiment, the surrounding object information acquisition unit 223 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 223 may acquire the distance and relative speed of at least one vehicle located at the front side, lateral side, and / or rear side of the vehicle.

[0060] According to one embodiment, the processor 130 may determine whether the functions required for autonomous driving can operate normally based on the vehicle state information. The functions required for autonomous driving may include, for example, a lane detection function, a lane change function, a lateral control function, a deceleration (or braking) control function, an acceleration control function, a powertrain control function, a safety area detection function, and at least one of an obstacle recognition and distance detection function. When at least one function required for autonomous driving cannot operate normally, the processor 130 may determine that normal autonomous driving cannot be performed.

[0061] According to one embodiment, the processor 130 may determine whether the vehicle state 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. When the vehicle state is not suitable for general driving conditions, the processor 130 may determine that normal autonomous driving is not possible. For example, when the vehicle cannot be driven due to tire pressure or engine overheating, the processor 130 may determine that normal autonomous driving is not possible.

[0062] According to an embodiment, the processor 130 may determine whether the environment around the vehicle is suitable for an operation design domain (ODD) of autonomous driving based on at least one piece of surrounding environment information. The operation design domain may represent the conditions of the surrounding environment in which autonomous driving operates normally. When the surrounding environment information of the vehicle does not match the operation design domain, the processor 130 may determine that normal autonomous driving cannot be performed.

[0063] According to various embodiments, when normal autonomous driving is not possible, the processor 130 may determine that this is a situation where a minimum risk maneuver is required to minimize the risk of an accident. When this is a situation where a minimum risk maneuver is required, the processor 130 may use the MRM strategy determination unit 240 to select a minimum risk maneuver strategy from a plurality of minimum risk maneuver strategies. The minimum risk maneuver strategy may include, for example, Figure 3 For example, the minimum risk maneuver strategy includes the traffic lane stop 301 strategy (which includes type 1 and type 2) and the shoulder stop 303 strategy (which includes type 3 and type 4).

[0064] 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.

[0065] The straight parking 311 of type 1 is a parking type that uses only the deceleration control 323, which is a longitudinal deceleration function and does not involve lateral control. For example, in a case where lane detection is not possible or lateral control is not possible due to a defect of an actuator, the straight parking 311 may be performed. In the case of the straight parking 311 of type 1, the acceleration control 322 and the lane change 324 are prohibited or impossible, and the function of detecting a potential parking position 325 outside the traffic lane may not be required. Here, detecting a potential parking position outside the lane may refer to a function of detecting the position of a safe area (such as a shoulder or a sleepy rest area) located outside the traffic lane.

[0066] The type 2 in-lane parking 312 is a type of parking within the boundary of the lane in which the vehicle is traveling. For example, the in-lane parking 312 may refer to a type in which the vehicle is stopped within the boundary of the lane in which the vehicle is traveling by lateral control 321 and / or deceleration control 323. The driving lane may refer to the lane in which the vehicle is traveling at the time point when it is determined that the minimum risk maneuver needs to be performed. In the case of the in-lane parking 312, the acceleration control 322 and the lane change 324 are prohibited, and the function of detecting a potential parking position outside the traffic lane may not be required.

[0067] Type 3 half shoulder parking 313 is a type of parking when a part of the vehicle is located on the shoulder of the road, and type 4 full shoulder parking 314 is a type of parking when the entire vehicle is stopped on the shoulder of the road. Functions of lateral control 321, deceleration control 323, lane change 324, and detection of a potential parking position outside a traffic lane 325 may be used in half shoulder parking 313 and full shoulder parking 314, and acceleration control 322 may be used only to maintain the current speed.

[0068] According to one embodiment, the priority of the above-mentioned MRM types may be determined based on the road, the surrounding environment, and the failure operation capability of the vehicle. For example, in order to minimize the risk when parking, the priority of the MRM type corresponding to the shoulder parking 303 strategy may be set higher than the priority of the MRM type corresponding to the traffic lane parking 301 strategy. In addition, the priority of the full shoulder parking 314 may be set higher than the priority of the half shoulder parking 313, and the priority of the parking in the lane 312 may be set higher than the priority of the straight line parking 311. That is, the priority of the MRM type may be set to decrease in the order of the full shoulder parking 314, the half shoulder parking 313, the parking in the lane 312, and the straight line parking 311.

[0069] According to various embodiments, the MRM strategy determination unit 240 of the processor 130 may select the MRM strategy based on at least one of the vehicle state information and the surrounding environment information.

[0070] According to one embodiment, the MRM strategy determination unit 240 may confirm the MRM type that can be executed among the above-mentioned MRM types based on the vehicle state information, based on the function that operates normally and / or the function that cannot operate normally among the functions required for autonomous driving. For example, when the lateral control 321 function operates normally, it can be determined that all of the straight line parking 311, the lane parking 312, the half shoulder parking 313, and the full shoulder parking 314 can be executed. As another example, when the lateral control 321 function does not operate normally, the executable MRM type may be determined to include only the straight line parking 311.

[0071] When it is confirmed based on the vehicle state information that there is only one MRM type that can be executed, the MRM strategy determination unit 240 may determine that the MRM type is the MRM strategy. For example, since only straight parking 311 can be executed when the lateral control 321 function cannot operate normally, the MRM strategy determination unit 240 may determine straight parking 311 as the MRM strategy. As another example, when the driving lane is not detected due to a sensor defect and / or an external environment, since only straight parking 311 can be executed, the MRM strategy determination unit 240 may determine straight parking 311 as the MRM strategy.

[0072] When it is confirmed that there are multiple MRM types that can be executed based on the vehicle state information, the MRM strategy determination unit 240 can determine one MRM type that can be executed within a specified minimum risk condition (MRC) range. According to one embodiment, the specified MRC range can be set and / or changed by an operator and / or a designer. According to one embodiment, the specified MRC range can be set differently according to vehicle performance, vehicle type, and / or external environmental factors (e.g., weather, time, etc.).

[0073] According to one embodiment, the MRM strategy determination unit 240 may determine the MRM type that can be performed within the specified MRC range based on whether there is a shoulder within the specified MRC range. When there is no shoulder within the specified MRC range, the MRM strategy determination unit 240 may determine the lane parking 312 or the straight line parking 311 as the MRM type that can be performed within the MRC range.

[0074] When there is a shoulder within the specified MRC range, the MRM strategy determination unit 240 can determine the MRM type that can be performed within the MRC range based on the size of the shoulder. When the size of the shoulder within the specified MRC range is greater than or equal to the specified size, the MRM strategy determination unit 240 can determine full shoulder parking 314, half shoulder parking 313, lane parking 312, or straight line parking 311 as the MRM type that can be performed within the MRC range. The specified size can be determined based on the size of the vehicle. When the size of the shoulder is less than the specified size, the MRM strategy determination unit 240 can determine half shoulder parking 313, lane parking 312, or straight line parking 311 as the MRM type that can be performed within the MRC range.

[0075] According to various embodiments, when there are a plurality of MRM types that can be executed within a designated MRC range, the MRM policy determination unit 240 may select a final MRM policy in consideration of priority and / or surrounding object information.

[0076] According to an embodiment, when there are multiple MRM types that can be executed within the specified MRC range, the MRM policy determination unit 240 may select the MRM type with the highest priority from among the MRM types that can be executed within the specified MRC range as the final MRM policy.

[0077] Figure 4 is a flow chart illustrating operations for performing a minimal risk maneuver of a vehicle, according to various implementations.

[0078] Reference Figure 4, in operation S10, the vehicle 100 may obtain a request to start a minimum risk maneuver (MRM). According to one embodiment, when the engine of the vehicle 100 is turned on and the vehicle 100 starts to move at a predetermined speed or higher, the processor 130 may generate a request for starting a minimum risk maneuver function. Alternatively, the processor 130 may obtain state information of the vehicle 100 and the surrounding environment of the vehicle 100, and generate a minimum risk maneuver request based on the obtained state information. Alternatively, the processor 130 may obtain a minimum risk maneuver request received through the communication device 150 or the sensor 110 from the outside. The minimum risk maneuver request may mean a command to instruct the vehicle 100 to perform a minimum risk maneuver.

[0079] In operation S20 , when there is a minimum risk maneuver request, the vehicle 100 may perform a minimum risk maneuver function.

[0080] The minimum risk maneuvering function may include an operation of monitoring a state of a vehicle ( S21 ), an operation of determining an MRM type ( S23 ), and an operation of executing the determined MRM type ( S25 ).

[0081] When the minimum risk maneuver request is obtained (S10), in operation S21, the vehicle 100 may monitor the state of the vehicle 100. In operation S21, the vehicle 100 may check the state of the autonomous driving system and / or the vehicle, analyze the severity when a fault exists, and identify the impact on the autonomous driving system and / or the vehicle. In addition, the vehicle 100 may check the state of related system components to determine the performance and capability of the current dynamic driving task (DDT) of the autonomous driving system.

[0082] According to one embodiment, the vehicle 100 may use the vehicle state information acquisition unit 210 and the surrounding environment information acquisition unit 220 to monitor the state of the components of the vehicle 100 and the environmental information around the vehicle 100. The vehicle 100 may monitor the state of each component of the vehicle 100 and the environmental information around the vehicle 100 in real time, such as lanes, surrounding vehicle information, etc. The vehicle 100 may determine which sensors or components of the sensor 110 are currently available (or operable).

[0083] In operation S23, the vehicle 100 may determine the type of MRM for emergency parking based on the acquired vehicle state information and surrounding environment information. Figure 3 As shown, the MRM type of vehicle may include direct parking, lane parking, half shoulder parking, and full shoulder parking. However, it is not limited thereto, and additional MRM types may be included in other embodiments.

[0084] The vehicle 100 can determine the MRM type suitable for the current fault state based on the determination result of the fault state. According to one embodiment, when only deceleration control of the vehicle can be performed, only direct parking can be selected as the type that can be realized. According to another embodiment, when steering control and deceleration control of the vehicle can be performed, in addition to straight-line parking, the type of parking in the lane can also be selected. According to another embodiment, when the lane change function and shoulder detection function in the autonomous driving function as well as the steering control and deceleration control of the vehicle can be performed, the types of half-shoulder parking and full-shoulder parking can also be selected.

[0085] When the vehicle 100 performs the MRM type determined in operation S25 according to the determination in operation S23 and eventually reaches the minimum risk state 30 (eg, a stop state), the minimum risk maneuver function may be terminated.

[0086] According to one embodiment, generally, the vehicle 100 maintains the initial MRM type determined in operation S23, and accordingly performs MRM in operation S25. When an internal or external factor changes seriously or when it is determined that the selected MRM type cannot be performed due to a change in traffic conditions, the vehicle 100 may change the MRM type. At this time, when the MRM type needs to be changed while performing the MRM that has been determined in operation S25, the vehicle 100 may change the MRM type in a reasonable and safe manner without delaying the achievement of the minimum risk condition.

[0087] According to one embodiment, when the vehicle 100 is performing the minimum risk maneuvering function, when a person (including the driver) intervenes 40 to take over the DDT at any point in time, all autonomous driving functions including the minimum risk maneuvering function may be terminated and the person may gain control of the vehicle.

[0088] As mentioned above, in Figure 4 The operation of determining the MRM type in operation S23 may be performed by the MRM strategy determination unit 240 of the vehicle 100 .

[0089] According to one embodiment, the MRM strategy determination unit 240 may generate a vehicle control command based on the determined MRM type and / or target point and send the vehicle control command to the controller 120, and the controller 120 may control the vehicle 100 based on the command to execute the determined MRM type and make the vehicle 100 meet the minimum risk condition at the target point. According to another embodiment, the controller 120 may obtain the MRM type and the target point from the MRM strategy determination unit 240, and perform vehicle control by itself, so that the MRM type is executed and the vehicle 100 meets the minimum risk condition at the target point.

[0090] The MRM strategy determination unit 240 may determine the MRM type based on the vehicle state information and the surrounding environment information, and simultaneously determine a point satisfying a minimum risk condition (ie, a target point at which the vehicle 100 is to stop).

[0091] As described above, the MRM type may have a priority set to be decreased in the order of full shoulder parking 314, half shoulder parking 313, lane parking 312, and straight line parking 311. Therefore, in cases other than special cases, such as when the lateral control 321 function cannot be normally operated, the MRM strategy determination unit 240 may determine the MRM type according to the above priority.

[0092] However, when the stop target point of the half shoulder parking corresponds to a safe place close to the current position of the vehicle, selecting the half shoulder parking instead of the full shoulder parking with the stop target point far away may be a more reasonable minimum risk maneuver. That is, the MRM type is determined by the MRM strategy determination unit 240 based on the complexity of the route to the stop point and the parking risk at the stop point, rather than simply determining the MRM type based on the set priority, which may further contribute to the safety of the vehicle.

[0093] Figure 5 is a flow chart illustrating operations for determining a target point and MRM type considering route complexity and parking risk when performing a minimum risk maneuver of a vehicle according to various embodiments.

[0094] When there is Figure 4 When an MRM request is shown, the vehicle 100 or the MRM strategy determination unit 240 may calculate a maximum distance or a maximum time that can be traveled in the MRM state in operation S510.

[0095] According to one embodiment, the vehicle 100 can calculate the maximum distance or maximum time that can be traveled in the MRM state based on the vehicle state information. The time until a serious risk event occurs can be calculated by calculating the fault tolerance time at the time point when the MRM is triggered. In addition, according to one embodiment, the vehicle 100 can detect the factors that cause the failure and calculate the fault tolerance time including the time period for executing the safety mechanism.

[0096] Figure 6 is a diagram illustrating an example of calculating a maximum time that can be traveled in a fault state according to various embodiments.

[0097] refer to Figure 6In the first embodiment, although a fault causing malfunction of the vehicle 100 occurs (S610), the safety mechanism for handling the fault may not be operated or cannot be operated. Then, after the fault tolerance time 615, a risk event caused by the malfunction may occur (S613). In the first embodiment, the fault tolerance time 615 can be considered as the time from the occurrence time point of the fault causing the malfunction (S610) to the occurrence of the risk event (S613) due to the malfunction.

[0098] refer to Figure 6 In the second embodiment, when a fault (S623) causing a malfunction (S620) is detected, the vehicle 100 may execute a safety mechanism (S625). According to an embodiment, the vehicle 100 may periodically (i.e., at regular time intervals) perform a diagnostic test (S621). When the diagnostic test (S621) is performed after the fault (S620) causing a malfunction is detected, the fault (S623) is detected after the fault detection time 622, and when the fault is detected, the vehicle 100 may respond to the fault by executing a safety mechanism (S625), and switch to a safe state (S627) after a predetermined period of time. In the second embodiment, the fault tolerance time 624 may be considered to be the time from the time point when the fault (S623) is detected to the time point when the safe state (S627) is switched.

[0099] refer to Figure 6 In the third embodiment, when a fault (S632) causing a malfunction (S630) is detected, the vehicle 100 may execute a safety mechanism (S635) including an emergency operation. According to an embodiment, the vehicle 100 may perform a diagnostic test (S631) periodically (i.e., at regular time intervals). When the diagnostic test (S631) is performed after the fault (S630) causing a malfunction is detected, the fault (S633) is detected after the fault detection time 632, and when the fault is detected, the vehicle 100 may respond to the fault by executing a safety mechanism (S635), the emergency operation may be performed during the emergency operation time 638 after the fault handling time 634, and when the emergency operation is completed, the vehicle 100 may switch to a safe state (S637). In the third embodiment, the fault tolerance time 639 may be regarded as the time from the time point when the fault (S633) is detected to the time point when the switch to the safe state (S637) is completed. Alternatively, according to another embodiment, the fault tolerance time may be the same as the emergency operation time 638 starting from the time point of completing the process of handling the fault to the time point of switching to the safe state (S637).

[0100] When the error tolerance time is determined, the vehicle 100 may determine the error tolerance distance based on the expected speed information of the vehicle 100 using the traffic flow information of the road where the vehicle is currently located.

[0101] Reference again Figure 5 In operation S520, the vehicle 100 may search for an all-shoulder parking area that can be reached within the maximum distance or maximum time that can be traveled calculated in operation S510.

[0102] Figure 7 is shown for explanation Figure 5 A diagram of an example of the operation of .

[0103] refer to Figure 7 In an embodiment, the vehicle 100 may search for an all-shoulder parking area that can be reached within the maximum distance or maximum time that can be traveled. According to an embodiment, an area where all-shoulder parking is possible may be calculated taking into account the size of the vehicle 100, and the vehicle 100 may determine whether all-shoulder parking is possible by grasping the size of an empty shoulder area and the presence of obstacles. Figure 7 In the example of , a full-shoulder parking area can be indicated by a black circle.

[0104] In operation S530, the vehicle 100 may determine whether there is a parking area with a route complexity lower than or equal to a preset value among the searched multiple all-shoulder parking areas. Here, factors such as the number of intersections to be passed, the number of left turns, the number of right turns, and the distance to the destination may be considered to calculate the route complexity. For example, the route complexity may be calculated by assigning 3 points to a left turn, 2 points to a right turn, and 1 point to a distance of 1 km. Figure 7 In the example of , the route complexity of the parking area 710 may be calculated as a total of 6 points, which is one left turn (3 points) + one right turn (2 points) + a distance of 1 km (1 point), and due to this distance, the value of the route complexity of the parking area 711 may be greater than the value of the route complexity of the parking area 710.

[0105] According to one embodiment, the route complexity may be calculated by assigning different weights to each of the above factors and determining the contribution of each factor based on the weights. Figure 7 In the example of , there are three all-shoulder parking areas, and the route complexity of two all-shoulder parking areas 710 and 711 may be lower than or equal to a preset value.

[0106] In operation S530, when the vehicle 100 determines that there is a parking area with a route complexity lower than or equal to a preset value, the vehicle 100 may proceed to operation S540, set the parking area with the lowest route complexity as the target point, and select full shoulder parking as the MRM type. Figure 7In the example of , the vehicle 100 may set the area with the lowest route complexity (eg, 710 ) as the final destination point among the two areas 710 and 711 with route complexities lower than or equal to a preset value.

[0107] When the vehicle 100 determines that there is no parking area with a route complexity lower than or equal to a preset value as a result of the determination of operation S530, the vehicle 100 may proceed to operation S550 to search for a half-shoulder parking area and determine whether there is a half-shoulder parking area with a route complexity lower than that of the full-shoulder parking area. According to another embodiment, in operation S550, the vehicle 100 may also determine whether there is a half-shoulder parking area with a route complexity lower than a preset value.

[0108] When the vehicle 100 determines that there is no half-shoulder parking area satisfying the corresponding condition as a result of the determination of operation S550, the vehicle 100 may proceed to operation S580 and select in-lane parking or straight-line parking as the MRM type.

[0109] When, as a result of the determination of operation S550, the vehicle 100 can determine that there is a half-shoulder parking area that meets the corresponding conditions, the vehicle 100 can proceed to operation S560, and determine whether the parking risk at the half-shoulder parking area that meets the corresponding conditions is lower than the preset risk. Here, the parking risk can be calculated based on the size of the parking area, whether it is a prohibited parking area such as a sidewalk, fire protection facilities, etc., the maximum speed information of the road, traffic flow information, etc., and the parking risk can be calculated by assigning different weights to each factor. For example, when the half-shoulder parking area does not correspond to a designated prohibited parking area, 0 points can be set, otherwise 3 points can be set; and when the maximum speed of the road is 40Km / h, 1 point can be set, when it is 50Km / h, 2 points can be set, and when it is 60Km / h, 3 points can be set. In addition, with Figure 7 Taking the half-shoulder parking area 720 in the figure as an example, when the half-shoulder parking area does not correspond to a designated no-parking area (0 points), and the maximum speed on the road is 40 km / h (1 point), and the degree of road occupancy is 1 / 4 (1 point), the parking risk can be calculated as 2 points.

[0110] When there is no half-shoulder parkable area having a parking risk lower than a preset risk as a result of the determination of operation S560, the vehicle 100 may proceed to operation S580 and select in-lane parking or straight line parking as the MRM type.

[0111] When there is a half-shoulder parking area with a parking risk lower than a preset risk (e.g., 3 points) as a result of the determination of operation S560, the vehicle 100 may proceed to operation S570 and select half-shoulder parking as the MRM type by setting the half-shoulder parking area with the lowest parking risk as a target point.

[0112] refer to Figure 7 In the example of , there are half-shoulder parking areas 720 and 721 whose route complexity is lower than that of the full-shoulder parking area, and among the parking areas 720 and 721, the half-shoulder parking area 720 with the lowest parking risk is selected as the target point.

[0113] Figure 8 is a flow chart illustrating operations for determining a target point and an MRM type taking into account route complexity and parking risk when performing a minimum risk maneuver of a vehicle according to other embodiments.

[0114] When there is Figure 4 When an MRM request is shown, the vehicle 100 or the MRM strategy determination unit 240 may calculate a maximum distance or a maximum time that can be traveled in the MRM state in operation S810.

[0115] According to one embodiment, the vehicle 100 can calculate the maximum distance or maximum time that can be traveled in the MRM state based on the vehicle state information. The time until a serious risk event occurs can be calculated by calculating the fault tolerance time at the time point when the MRM is triggered. In addition, according to one embodiment, the vehicle 100 can detect the factors that cause the failure and calculate the fault tolerance time including the time period for executing the safety mechanism. Figure 6 An example of calculating the error tolerance time is shown in , and since the example has been described, its description is omitted here.

[0116] In operation S820, the vehicle 100 may search for a full-shoulder parking area and a half-shoulder parking area that can be reached within the maximum distance or maximum time that can be traveled calculated in operation S810.

[0117] In operation S830, the vehicle 100 may calculate the route complexity and parking risk at the searched full-shoulder parking area and half-shoulder parking area. Here, the route complexity may be calculated equally for the full-shoulder parking area and the half-shoulder parking area. As described above, the route complexity may be calculated by considering factors such as the number of intersections to be passed, the number of left turns, the number of right turns, and the distance to the destination. For example, the route complexity may be calculated by assigning a score of 3 points to a left turn, 2 points to a right turn, and 1 point to a distance of 1 km. Figure 7In the example of , the route complexity of the parking area 710 may be calculated as a total of 6 points, which is one left turn (3 points) + one right turn (2 points) + a distance of 1 km (1 point), and due to this distance, the value of the route complexity of the parking area 711 may be greater than the value of the route complexity of the parking area 710.

[0118] According to one embodiment, route complexity may be calculated by assigning different weights to each of the above factors and determining the contribution of each factor based on the weights.

[0119] The parking risk may be calculated only for the half-shoulder parking area. In the case of the full-shoulder parking area, since the entire vehicle can enter the shoulder parking area, the parking risk may be regarded as 0. The parking risk in the half-shoulder parking area may be calculated based on the size of the parking area, whether it is a prohibited parking area such as a sidewalk, a fire facility, etc., the maximum speed information of the road, the traffic flow information, etc., and the parking risk may be calculated by assigning different weights to each factor.

[0120] In operation S840, the vehicle 100 may determine whether there is a parking area where the parking risk is lower than a preset risk and the route complexity is lower than or equal to a preset value. In the case of a full-shoulder parking area, since the parking risk of the vehicle 100 may be considered to be 0, it may only be determined whether the route complexity is lower than or equal to a preset value. For example, the vehicle 100 may calculate Figure 7 The full-shoulder parking areas 710 and 711 and the half-shoulder parking area 720 meet the conditions of operation S840 based on the route complexity and parking risk of the full-shoulder parking areas (black circles) and the half-shoulder parking areas (black squares).

[0121] When the vehicle 100 determines that there is no parkable area satisfying the condition of operation S840 as a result of the determination of operation S840 , the vehicle 100 may proceed to operation S870 and select in-lane parking or straight-line parking as the MRM type.

[0122] When the vehicle 100 determines that there is a parking area that satisfies the condition of operation S840 as a result of the determination of operation S840, in operation S850, the vehicle 100 may select a parking area with the lowest route complexity among the parking areas with a parking risk lower than a preset risk. Figure 7 In the example of FIG. 1 , vehicle 100 may select half-shoulder parking area 720 .

[0123] The vehicle 100 may determine whether the parkable area selected in operation S860 is an all-shoulder parkable area, and when it is an all-shoulder parkable area, the vehicle 100 may proceed to operation S880, select all-shoulder parking as the MRM type, and set the parkable area selected in operation S850 as a target point.

[0124] When the vehicle 100 determines that the parkable area selected in operation S860 is not a full-shoulder parkable area, the vehicle 100 may proceed to operation S890, select half-shoulder parking as the MRM type, and set the parkable area selected in operation S850 as a target point.

[0125] As described above, various embodiments propose a method that improves safety while minimizing the risk of a vehicle when a failure occurs during autonomous driving and performs a minimum risk maneuver (MRM) function to achieve a minimum risk condition (i.e., a stopped state) by selecting an MRM type and a target point based on route complexity and parking risk in each parkable area.

[0126] According to various embodiments of the document, when the vehicle detects a situation in which normal autonomous driving is impossible during autonomous driving and determines to stop on the shoulder using a minimum risk maneuvering strategy, the vehicle risk is minimized and safety can be improved because the optimal parking type and parking location are determined by determining the route complexity and parking risk.

Claims

1. An autonomous vehicle comprising: at least one sensor for detecting the surroundings of the vehicle and generating surroundings information; a processor for generating vehicle status information by monitoring the status of the vehicle and controlling autonomous driving of the vehicle; and a controller for controlling the operation of the vehicle according to the control of the processor, Wherein, the processor is configured to: during autonomous driving of the vehicle, determining whether a minimum risk maneuver is required based on at least one of the surrounding environment information and the vehicle state information, determining a type of minimal risk maneuver and a target point at which the vehicle is to stop when the minimal risk maneuver is required, and Based on the determined minimum risk maneuver type and the target point, the vehicle is controlled to stop at the target point.

2. The autonomous vehicle of claim 1, wherein: The processor is further configured to: Calculate the maximum distance or maximum time that can be traveled in the least risky maneuvering state, Search for a parking area that can be reached within the maximum distance or the maximum time, Classify the searched parking areas into full-shoulder parking areas and half-shoulder parking areas, calculating at least one of route complexity and parking risk of each of the all-shoulder parking areas, determining whether parking is possible in the all-shoulder parking area based on the at least one of the calculated route complexity and parking risk, and When parking is not possible in all the full-shoulder parking areas, calculating at least one of route complexity and parking risk for each of the half-shoulder parking areas, and The minimum risk maneuver type and the target point where the vehicle is to stop are determined based on the at least one of the route complexity and the parking risk of the semi-shoulder parking area.

3. The autonomous vehicle of claim 1, wherein: The processor is further configured to: Calculate the maximum distance or maximum time that can be traveled in the least risky maneuvering state, Search for a parking area that can be reached within the maximum distance or the maximum time, calculating at least one of the route complexity and the parking risk of each of the parking areas, and The least risky maneuver type and the target point where the vehicle is to stop are determined based on the at least one of the route complexity and the parking risk of the parkable area.

4. The autonomous vehicle of claim 3, wherein: The processor is further configured to: Search for a full-shoulder parking area that can be reached within the maximum distance or the maximum time, Calculate the route complexity of each of the searched all-shoulder parking areas, determining a full-shoulder parking area having a route complexity lower than or equal to a preset value and having the lowest route complexity as the target point where the vehicle is to stop, and A full shoulder stop is identified as the least risky maneuver type.

5. The autonomous vehicle of claim 4, wherein: The processor is further configured to: When there is no full-shoulder parking area whose route complexity is lower than or equal to the preset value, searching for a half-shoulder parking area that can be reached within the maximum distance or the maximum time, When there is a half-shoulder parking area whose route complexity is lower than that of the full-shoulder parking area and whose parking risk is lower than a preset risk, the half-shoulder parking area with the lowest parking risk is determined as the target point where the vehicle is to stop, and half-shoulder parking is determined as the minimum risk maneuver type, and When there is no half-shoulder parking area having a route complexity lower than that of the full-shoulder parking area, parking in a lane or parking in a straight line is determined as the minimum risk maneuver type.

6. The autonomous vehicle of claim 4, wherein: The processor is configured to: When there is no full-shoulder parking area whose route complexity is lower than or equal to the preset value, searching for a half-shoulder parking area that can be reached within the maximum distance or the maximum time, When there is a half-shoulder parking area with the route complexity lower than or equal to the preset value and the parking risk lower than the preset risk, the half-shoulder parking area with the lowest parking risk is determined as the target point where the vehicle is to stop, and half-shoulder parking is determined as the minimum risk maneuver type, and When there is no half-shoulder parking area with the route complexity lower than or equal to the preset value, parking in a lane or parking in a straight line is determined as the minimum risk maneuver type.

7. The autonomous vehicle of claim 3, wherein: The processor is further configured to: Search for full-shoulder parking areas and half-shoulder parking areas that can be reached within the maximum distance or the maximum time, Calculating the route complexity and parking risk of each of the full-shoulder parking areas searched and each of the half-shoulder parking areas searched, and When there is no parking area where the parking risk is less than a preset risk and the route complexity is less than or equal to a preset value, parking in a lane or parking in a straight line is selected as the minimum risk maneuver type.

8. The autonomous vehicle of claim 7, wherein: The processor is further configured to: When there is a parking area where the parking risk is less than the preset risk and the route complexity is less than or equal to the preset value, the parking area with the lowest route complexity is selected from the parking areas where the parking risk is less than the preset risk. When the selected parking area is an all-shoulder parking area, determining all-shoulder parking as the minimum risk maneuver type, and determining the selected parking area as the target point, and When the selected parking area is not a full-shoulder parking area, half-shoulder parking is determined as the minimum risk maneuver type, and the selected parking area is determined as the target point.

9. The autonomous vehicle of claim 2, wherein: The processor is further configured to calculate the route complexity based on the number of intersections to be traversed, the number of left turns, the number of right turns, and the distance to the destination.

10. The autonomous vehicle of claim 2, wherein: The processor is further configured to calculate the parking risk based on the size of the parking area, whether the area is a no-parking area, maximum speed information of the road, and traffic flow information.

11. A method for operating a vehicle, the method comprising: During autonomous driving of the vehicle, obtaining at least one of surrounding environment information and vehicle state information; determining whether a minimum risk maneuver is required based on the at least one of the surrounding environment information and the vehicle state information; When it is determined that the minimum risk maneuver is required, determining a minimum risk maneuver type and a target point at which the vehicle is to stop; as well as Based on the determined minimum risk maneuver type and the target point, the vehicle is controlled to stop at the target point.

12. The method for operating a vehicle according to claim 11, wherein: Determining the minimum risk maneuver type and the target point includes: Calculate the maximum distance or maximum time that can be traveled with minimal risk; Searching for a parking area that can be reached within the maximum distance or the maximum time; Classify the searched parking areas into full-shoulder parking areas and half-shoulder parking areas; calculating at least one of route complexity and parking risk at the all-shoulder parking area; determining whether parking is possible in the all-shoulder parking area based on the at least one of the calculated route complexity and parking risk; and When parking is not possible in all of the full-shoulder parking areas, calculating at least one of route complexity and parking risk at the half-shoulder parking area, and The minimum risk maneuver type and the target point where the vehicle is to stop are determined based on the at least one of route complexity and parking risk at the semi-shoulder parking area.

13. The method for operating a vehicle according to claim 11, wherein: Determining the minimum risk maneuver type and the target point further includes: Calculate the maximum distance or maximum time that can be traveled with minimal risk; Searching for a parking area that can be reached within the maximum distance or the maximum time; Calculating at least one of route complexity and parking risk for each of the parkingable areas; and Based on the route complexity and the parking risk of the parking area, a minimum risk maneuver type and the target point where the vehicle is to stop are determined.

14. The method for operating a vehicle according to claim 13, wherein: Determining the minimum risk maneuver type and the target point further includes: Searching for a full-shoulder parking area that can be reached within the maximum distance or the maximum time; Calculate the route complexity of the searched full-shoulder parking area; determining the all-shoulder parking area where the route complexity is lower than or equal to a preset value and the route complexity value is the lowest as the target point where the vehicle is to stop; and A full shoulder stop is identified as the least risky maneuver type.

15. The method for operating a vehicle according to claim 14, wherein: Determining the minimum risk maneuver type and the target point further includes: When there is no full-shoulder parking area whose route complexity is less than or equal to the preset value, searching for a half-shoulder parking area that can be reached within the maximum distance or the maximum time; When there is a half-shoulder parking area having a lower route complexity than that of the full-shoulder parking area and a parking risk lower than a preset risk, determining the half-shoulder parking area with the lowest parking risk as the target point at which the vehicle is to stop, and determining half-shoulder parking as the minimum risk maneuver type; and When there is no half-shoulder parking area having a route complexity lower than that of the full-shoulder parking area, parking in a lane or parking in a straight line is determined as the minimum risk maneuver type.

16. The method for operating a vehicle according to claim 14, wherein: Determining the minimum risk maneuver type and the target point further includes: When there is no full-shoulder parking area whose route complexity is less than or equal to the preset value, searching for a half-shoulder parking area that can be reached within the maximum distance or the maximum time; When there is a half-shoulder parking area with the route complexity lower than or equal to the preset value and the parking risk lower than the preset risk, determining the half-shoulder parking area with the lowest parking risk as the target point where the vehicle will stop, and determining half-shoulder parking as the minimum risk maneuver type; and When there is no half-shoulder parking area with the route complexity lower than or equal to the preset value, parking in a lane or parking in a straight line is determined as the minimum risk maneuver type.

17. The method for operating a vehicle according to claim 13, wherein: Determining the minimum risk maneuver type and the target point further includes: Searching for full-shoulder parking areas and half-shoulder parking areas that can be reached within the maximum distance or the maximum time; Calculating the route complexity and parking risk of each of the full-shoulder parking areas searched and each of the half-shoulder parking areas searched; and When there is no parking area where the parking risk is less than a preset risk and the route complexity is less than or equal to a preset value, parking in a lane or parking in a straight line is selected as the minimum risk maneuver type.

18. The method for operating a vehicle according to claim 17, wherein: Determining the minimum risk maneuver type and the target point further includes: When there is a parking area where the parking risk is less than the preset risk and the route complexity is less than or equal to the preset value, select the parking area with the lowest route complexity among the parking areas where the parking risk is less than the preset risk; When the selected parking area is an all-shoulder parking area, determining all-shoulder parking as the minimum risk maneuver type, and determining the selected parking area as the target point; and When the selected parking area is not a full-shoulder parking area, half-shoulder parking is determined as the minimum risk maneuver type, and the selected parking area is determined as the target point.

19. The method for operating a vehicle according to claim 12, wherein: The route complexity is calculated based on the number of intersections to be passed, the number of left turns, the number of right turns, and the distance to the destination.

20. The method for operating a vehicle according to claim 12, wherein: The parking risk is calculated based on the size of the parking area, whether the area is a no-parking area, maximum speed information of the road, and traffic flow information.

Images