Method and apparatus for performing a minimal risk manipulation for automated driving

Abstract

A method of performing autonomous driving (MRM)-shoulder parking (SS) of a vehicle by an ADS includes generating a first potential parking position (PSL), determining a target parking position (TSL) based on the first potential parking position (PSL), and controlling shoulder parking of the vehicle based on the target parking position (TSL). Determining the TSL includes performing a first operation of the MRM based on determining that the TSL is unsuccessful, and controlling shoulder parking of the vehicle includes performing a second operation of the MRM based on determining that the TSL is difficult to reach.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of an earlier filing date and priority to Korean Application No. 10-2023-0147497, filed on October 31, 2023, which is hereby incorporated by reference in its entirety. Technical Field

[0003] Embodiments relate to a method and apparatus for performing a minimum risk maneuver for automated shoulder parking via an automated driving system (ADS). Background Art

[0004] Minimal risk manoeuvre (MRM) is a fallback function of an automated driving system (ADS) used to achieve a minimal risk condition (MRC), i.e., a stable parking state. When the ADS is performing a dynamic driving task, an event may occur that prevents the ADS from continuing the dynamic driving task. Examples of events may be one or more of the following: i) an error in the automated driving system, automated driving components, or other vehicle components for ISO / Society of Automotive Engineers (SAE) Level 3-5 ADS; ii) a risk of the ADS closing the operational design domain (ODD) for ISO / SAE Level 3 or 4 ADS [1]; iii) the inability of the fallback ready user (FRU) or passenger to take over the dynamic driving task when the automated driving system issues an intervention request for ISO / SAE Level 3 ADS.

[0005] For ISO / SAE Level 3-5 ADS, the vehicle can be involved in a collision or face another challenging situation. In this case, ADS will initiate the minimum risk maneuver function to provide greater safety for all passengers and other road users. The MRM function is to reduce the risk by considering the target vehicle condition and traffic conditions, selecting the most appropriate MRM type, and ultimately stopping the vehicle through vehicle control.

[0006] The international standard ISO 23793-1, 2 (Minimum Risk Maneuvering-1, 2, MRM-1, 2) discloses the concept of an automated driving vehicle reaching a minimum risk condition (MRC) through minimum risk maneuvering (MRM).

[0007] Conventional technologies, such as international standards ISO 23793-1 and 2, disclose control logic for the MRM roadshoulder stop (MRM-SS) function, but some logic needs to be modified / added to improve traffic safety and function efficiency. Summary of the invention

[0008] Embodiments provide an apparatus and method for performing automated driving minimal risk maneuvers for efficient and safe shoulder parking.

[0009] Embodiments provide an apparatus and method for an autonomous vehicle to safely and efficiently perform an autonomous minimal risk maneuver for shoulder parking.

[0010] Additional advantages, purposes and features of the present disclosure will be described in part in the following description, and in part will become apparent to those of ordinary skill in the art after studying the following, or may be learned from the practice of the present disclosure. The purposes and other advantages of the present disclosure may be realized and obtained by the structures specifically indicated in the written description and the technical solutions of the present disclosure and the accompanying drawings.

[0011] In one aspect of the present disclosure, a method for performing autonomous driving MRM-street shoulder parking SS of a vehicle through an autonomous driving system ADS includes: generating a first potential stopping location (PSL), determining a target stopping location (TSL) based on the first PSL, and controlling the vehicle's street shoulder parking based on the TSL, wherein determining the TSL may include performing a first operation of MRM based on determining that the TSL is unsuccessful, and wherein controlling the vehicle's street shoulder parking may include performing a second operation of MRM based on determining that the TSL is difficult to reach.

[0012] The first operation may be generating a second PSL different from the first PSL or changing the MRM type, the MRM type may be one of MRM type 1 for straight parking, MRM type 2 for in-lane parking, or MRM type 3 for shoulder parking, and changing the MRM type may include changing the MRM type from MRM type 3 to one of MRM type 1 and MRM type 2.

[0013] Changing the MRM type may include: changing the MRM type from MRM type 3 to MRM type 2 based on that at least one of the ADS communication module, sensing module and database is in a normal state; and changing the MRM type from MRM type 3 to MRM type 1 based on that the ADS communication module, sensing module and database are in an abnormal state.

[0014] The first operation may include: generating a second PSL based on that a preset condition is not satisfied; and changing the MRM type based on that the preset condition is satisfied.

[0015] The preset conditions may include: a condition that the number of times TSL is determined to be unsuccessful is greater than or equal to a threshold number; or a condition that data received from a leading vehicle or infrastructure through vehicle-to-everything (V2X) communication indicates that it is difficult to determine TSL.

[0016] The second operation may be changing the MRM type, the MRM type may be one of MRM type 1 for straight parking, MRM type 2 for in-lane parking, or MRM type 3 for shoulder parking, and changing the MRM type may include changing the MRM type from MRM type 3 to one of MRM type 1 and MRM type 2.

[0017] Changing the MRM type may include: changing the MRM type from MRM type 3 to MRM type 2 based on that at least one of the ADS communication module, sensing module and database is in a normal state; and changing the MRM type from MRM type 3 to MRM type 1 based on that the ADS communication module, sensing module and database are in an abnormal state.

[0018] Controlling the shoulder parking of the vehicle may include performing a second operation and a takeover alarm based on determining that the TSL is difficult to reach, and the takeover alarm may be at least one of a message alarm or a sound alarm for guiding the driver of the vehicle to take over.

[0019] In another general aspect, an automated driving system ADS for performing a minimum risk maneuver of an automated driving MRM-roadside parking SS of a vehicle includes: a transceiver; a memory; and one or more processors. The one or more processors are configured to perform operations including: generating a potential parking location (PSL); determining a target parking location (TSL) based on the PSL; and controlling roadside parking of the vehicle based on the TSL. Determining the TSL includes performing a first operation of the MRM based on determining that the TSL is unsuccessful. Controlling roadside parking of the vehicle includes performing a second operation of the MRM based on determining that the TSL is difficult to reach.

[0020] By means of the method / apparatus according to the embodiments, an automated driving minimum risk maneuver for road shoulder parking may be efficiently performed.

[0021] By means of the method / apparatus according to the embodiments, an automated driving minimal risk maneuver for road shoulder parking may be performed safely.

[0022] By means of the method / apparatus according to the embodiments, a minimum risk maneuver for automated driving of shoulder parking may be accurately performed.

[0023] Through the following detailed description, the further applicable scope of the present disclosure will become apparent. Those skilled in the art can clearly understand various changes and modifications within the spirit and scope of the present disclosure, and therefore it should be understood that the detailed description and specific embodiments (such as the preferred embodiments of the present disclosure) are given as examples only. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which are included to provide a further understanding of the present disclosure and are included in and constitute a part of this application, illustrate embodiments of the present disclosure and are used together with the specification to explain the principles of the present disclosure. In order to better understand the various embodiments described below, the description of the following embodiments should be read in conjunction with the accompanying drawings (including corresponding parts with the same reference numerals in the accompanying drawings). In the accompanying drawings:

[0025] Figure 1 shows a state diagram according to an embodiment;

[0026] Figure 2 shows a Minimum Risk Manipulation (MRM) according to an embodiment;

[0027] Figure 3 The MRM classification is shown;

[0028] Figure 4 A vehicle control device according to an embodiment is shown;

[0029] Figure 5 A vehicle structure according to an embodiment is shown;

[0030] Figure 6 shows a minimal risk maneuver for shoulder parking according to an embodiment;

[0031] Figure 7 illustrates operation of a minimum risk maneuver for shoulder parking in accordance with an embodiment;

[0032] Figure 8 illustrates operation of a minimum risk maneuver for shoulder parking in accordance with an embodiment; and

[0033] Fig. 9 A method for minimal risk maneuvering for shoulder parking according to an embodiment is shown. DETAILED DESCRIPTION

[0034] The preferred embodiments of the embodiments will be described in detail, examples of which are shown in the accompanying drawings. The following detailed description with reference to the accompanying drawings is intended to illustrate the preferred embodiments of the embodiments, rather than merely presenting embodiments implemented according to the embodiments. The following detailed description includes details that provide a thorough understanding of the embodiments. However, it will be apparent to those skilled in the art that the embodiments may be practiced without these details.

[0035] Although most of the terms used in the embodiments are selected from common terms widely used in the art, some terms are arbitrarily selected by the applicant and their meanings are explained in detail in the following description as needed. Therefore, the embodiments should be understood based on the intended meanings of the terms rather than their simple names or meanings.

[0036] Figure 1 A state diagram according to an embodiment is shown.

[0037] Figure 1 An example MRM state diagram of an MRM (3.1 Minimum Risk Maneuver) is shown. In different automated driving systems (ADS), the specific states and switching conditions of the MRM may vary.

[0038] Definitions of terms according to the embodiments are as follows.

[0039] Minimum Risk Maneuver (MRM) means an action performed by an ADS to achieve a minimum risk state. A Minimum Risk State (MRC) is a stable stationary state that a user or ADS can bring a vehicle to after a dynamic driving task (DDT) takes over, thereby reducing the risk of a collision when a given motion cannot or should not continue. A target vehicle is a vehicle equipped with an ADS capable of performing an MRM. Standstill management is an action taken by an ADS to maintain a vehicle in an MRC. Lane boundaries are lane boundaries determined by visible lane markings, or in the absence of visible lane markings, by incidental visible road features or other means (e.g., positioning associated with a digital map, magnetic markers, etc.). A shoulder is a portion of a roadway that is located at the edge of the road outside of a lane boundary to allow emergency vehicles to bypass traffic congestion or provide a place for problem vehicles to exit from moving traffic. Acceleration control means control that produces positive acceleration using a vehicle function (e.g., powertrain control). Deceleration control means control that produces negative acceleration using a vehicle function (e.g., brakes). ADS active means that the ADS executes the entire DDT in the ADS active state, which is the ADS normal operating state or the MRM state. When the state switches from ADS active to ADS inactive (B), the ADS deactivation procedure defined for each ADS of the active ADS continues to apply. ADS normal operation means that in the ADS normal operating state, the ADS executes the DDT for the expected operation of the system. In the ADS normal operating state, the ADS determines whether MRM is required. When it is determined that MRM is required, the ADS switches to MRM (A). In the minimum risk maneuvering state, the ADS controls its vehicle to reach the MRC state.

[0040] The abbreviations used in this paper are defined as follows: Automated Driving System (ADS), Dynamic Driving Task (DDT), Fallback-Ready User (FRU), Human Machine Interface (HMI), Minimal Risk Manoeuvre (MRM), Minimal Risk Condition (MRC), Object and Event Detection Response (OEDR), Operational Design Domain (ODD), Region of Interest (ROI), Request to Intervene (RTI), and Subject Vehicle (SV).

[0041] The MRM state operates as follows. ADS monitors the ADS state. ADS determines the type of MRM. ADS controls the target vehicle (SV) to perform MRM. ADS notifies other traffic participants of the MRM execution. In the case that the SV has passengers, ADS notifies all passengers in the SV of the MRM execution.

[0042] When the state switches from MRM to ADS Inactive (C), the default ADS enforcement conditions in the Inactive state may apply, but other conditions may apply during ongoing MRM.

[0043] In case the state switches from MRM to MRC(D), the vehicle speed is set to 0 (V_sv=0 [kph]), parking management is enabled, and the hazard warning lights are applied.

[0044] In the case of ADS inactivity, the ADS will be released from the state and no DDT function will be performed.

[0045] MRC is the state with the least risk, for example, the target vehicle is stable and stationary.

[0046] In the MRC state, the ADS performs parking management. The ADS turns on the hazard warning light. The ADS communicates with the activated human user.

[0047] As used herein, a vehicle may be referred to as a transportation vehicle, including robots, urban air mobility (UAM), and autonomous driving devices.

[0048] Figure 2A minimum risk maneuver (MRM) is shown according to an embodiment.

[0049] Figure 2 An example MRM process of MRM is shown. The detailed process of MRM may vary depending on the ADS.

[0050] When an ADS requests an MRM, the MRM is executed through the following steps:

[0051] Monitor ADS status: First, ADS checks the status of the system. It determines the current DDT working capability of ADS by analyzing the severity of the fault, confirming its impact on the system, and checking the status of related system components.

[0052] Determine MRM type: Select the most appropriate MRM type. This determination includes internal (system status) and external (e.g. traffic density, ODD) information. By default, it is recommended to maintain the MRM type selection. However, the type can be changed if significant internal or external factors change or if changes in traffic conditions make the selected MRM infeasible. In the event that the MRM type changes while the ADS is executing MRM, the ADS ensures that multiple MRM type changes do not delay the system from reaching MRC in a reasonable and safe manner. MRM implementation: Includes longitudinal and lateral control to execute the selected MRM. The above steps are iterated until the vehicle reaches an MRC state. During the MRM process, a human user can intervene and take over the DDT.

[0053] Figure 3 The MRM classification is shown.

[0054] Depending on the interior and exterior conditions of the ADS-equipped vehicle, the available MRMs may vary. Figure 3 As shown, MRM is classified into three types. The MRM types may be referred to as MRM type 1, MRM type 2, and MRM type 3. Based on the location of parking, MRM may be classified into traffic lane parking and shoulder parking. Depending on the embodiment, additional categories may be added.

[0055] MRM Type 1 represents a straight stop, in which lateral control may be unavailable, acceleration control may be prohibited, deceleration control may be available, lane changes may be prohibited, and detection of potential parking positions outside of traffic lanes may not be required.

[0056] MRM Type 2 represents lane parking, in which lateral control may be available, acceleration control may be prohibited, deceleration control may be used, lane changes may be prohibited, and detection of potential parking positions outside the lane may not be required.

[0057] MRM Type 3 represents shoulder parking, where lateral control may be available, acceleration control may optionally be used, deceleration control may be used, lane change may be used, and detection of potential parking positions outside the lane may be used.

[0058] Lane stopping is a method of emergency stopping among other road users when a target vehicle or its ADS has a serious malfunction. There are two types of lane stopping: through-the-lane stopping and in-lane stopping. Depending on the work area, lane stopping can affect the flow of traffic and can potentially cause a secondary collision.

[0059] Straight stop is a method of stopping the vehicle using only longitudinal control without active lateral control. Straight stop uses longitudinal deceleration control to stop the vehicle when lateral control is not available. Straight stop is only applied when lateral control cannot be available (e.g. lane detection failure, steering actuator failure) or there is no lane to follow in ODD (e.g. valet parking system).

[0060] Since lateral control is not available during through-stop MRM, the vehicle can cross lane boundaries or stop outside of the lane. Through-stop MRM includes only deceleration control.

[0061] Lane parking is a method of stopping the vehicle within the boundaries of the lane in which the vehicle is traveling when MRC is activated. Longitudinal deceleration and lateral control are used, along with environmental (sensors, map data, etc.) information about the path (and optional forward targets). Lane parking can be applied in situations where changing lanes is not possible or where it is not possible to reach a stopping position on the shoulder of the road. MRC is implemented within the boundaries of the current lane.

[0062] Shoulder Stop: For shoulder stop, both lateral and longitudinal control are used to ensure that the target vehicle is stopped as far away from the traffic as possible. As a result of the shoulder stop maneuver, at least a portion of the vehicle remains stationary outside the lane. The shoulder stop maneuver is intended to minimize the impact of the MRM on nearby road users and to help passengers exit the vehicle in a safe manner.

[0063] Shoulder parking uses both longitudinal and lateral control as well as information about the driving environment (sensors, map data or other means of driving environment perception) related to the road ahead and the relevant lanes. For shoulder parking, ADS can determine the location of the parking and determine whether the vehicle can reach the parking location.

[0064] Lane boundary crossings can be determined by ADS performing MRM, and the number of lane boundary crossings is unlimited. Lane changes are only made toward the target shoulder expected by MRC. Acceleration control can be performed when driving to a potential parking position if necessary for safe interaction with other vehicles. MRC can be implemented on hard shoulders by partially or completely removing the SV from the active lane.

[0065] Changing MRM Type: During MRM execution, additional relevant events may occur inside or outside the vehicle, or the ADS may identify additional information. When the ADS determines that it is not appropriate to achieve the originally intended MRC, the ADS may change the intended MRC to a lower MRM Type. The MRM Type can only be changed in one direction: from a higher type to a lower type. If the MRM Type is changed while the ADS is executing an MRM, the ADS ensures that multiple MRM Type changes do not delay the system from achieving the MRC in a reasonable and safe manner.

[0066] Figure 4 A vehicle control apparatus according to an embodiment is shown.

[0067] The vehicle control device 4000 according to the embodiment is a device for controlling the operation of the vehicle according to the embodiment. The vehicle control device may be referred to as an integrated autonomous driving vehicle controller 600. The vehicle control device may include an interface unit 4001, a processor 4002, and a memory 4003.

[0068] The memory may store instructions for performing operations according to the embodiments, signal information, data, etc. The memory may be connected to the interface unit and the processor to transmit and receive necessary signals.

[0069] The interface unit can receive signals, information, data, etc. transmitted to the vehicle control device and transmit them to the memory and / or processor. It can also transmit signals, information, data, etc. generated by the memory and / or processor to the vehicle and / or the driver and / or the passenger.

[0070] Based on the data and / or instructions stored in the memory, the processor may perform control operations of the vehicle according to an embodiment.

[0071] Figure 4 The vehicle control device may correspond to a device installed on the vehicle, or may correspond to a terminal device that controls the vehicle.

[0072] Figure 5 A vehicle structure according to an embodiment is shown.

[0073] The vehicle according to the embodiment can be Figure 5 The configuration shown in the figure can perform autonomous driving through an autonomous driving control system. The vehicle according to the embodiment can be referred to as an autonomous driving vehicle, a robot, an urban air mobility (UAM), an autonomous driving device, etc.

[0074] The autonomous driving vehicle 1000 may be implemented mainly based on an integrated autonomous driving vehicle controller 600, which sends and receives data required for autonomous driving control of the vehicle through a driving information input interface 101, a travel information input interface 201, an occupant output interface 301, and a vehicle control output interface 401. The integrated autonomous driving vehicle controller may be referred to herein as a controller, a processor, or simply a control unit.

[0075] Through the driving information input interface, in the vehicle's automatic driving mode or manual driving mode, the integrated automatic driving vehicle controller can obtain driving information based on the passenger's operation of the user input unit. The user input unit may include a driving mode switch and a control panel 120 (e.g., a navigation terminal installed on the vehicle, a smartphone or tablet computer carried by the passenger, etc.). Therefore, the driving information may include driving mode information and navigation information about the vehicle.

[0076] In addition, when it is determined that the driver needs to be warned in the automatic driving mode or manual driving mode of the vehicle, the integrated automatic driving vehicle controller can provide the driver with warning information and the above-mentioned driving state information through the passenger output interface. A speaker 310 and a display 320 can be included to output the driving state information and warning information audibly and visually. The display can be implemented as the same device as the above-mentioned control panel, or it can be implemented as a separate independent device.

[0077] In addition, through the vehicle control output interface, the integrated autonomous driving controller can transmit control information for controlling the driving of the vehicle in the autonomous driving mode or the manual driving mode to the sub-control system applied to the vehicle. The sub-control system for controlling the driving of the vehicle may include at least one of a motor control system, an engine control system, a brake control system, and a steering control system. Through the vehicle control output interface, the integrated autonomous driving vehicle controller can transmit at least one of the motor control information, the engine control information, the brake control information, and the steering control information as control information to each sub-control system.

[0078] The integrated automatic driving controller can obtain driving information based on the driver's operation and driving information indicating the vehicle's driving status through the driving information input interface and the driving information input interface respectively, and can provide driving status information and warning information generated based on the automatic driving algorithm through the passenger output interface.

[0079] In order to ensure reliable autonomous driving of the vehicle, the autonomous driving device according to an embodiment may include sensors configured to detect objects around the vehicle (such as adjacent vehicles, pedestrians, roads or fixed facilities (such as traffic lights, milestones, traffic signs, building fences, etc.)).

[0080] The sensor may include one or more of a lidar sensor, a radar sensor, and a camera sensor to detect nearby objects outside the vehicle. The sensor may include a front lidar sensor 511, a front radar sensor 521, a rear lidar sensor 513, a rear radar sensor 524, a left camera sensor 532, a right camera sensor 533, an interior camera sensor 535, a front camera sensor 531, and a rear camera sensor 534. The sensor may be associated with microphones 551 and 552.

[0081] Figure 6 A minimal risk maneuver for shoulder parking is shown in accordance with an embodiment.

[0082] The goal of the Minimal Risk Manoeuvre for AutomatedDriving Road Shoulder Stop (MRM-SS) is to provide both longitudinal and lateral control to stop the SV in a suitable location away from traffic. To select a suitable location, it is best to park the SV on a hard shoulder. However, in the event that a shoulder is not available, any space outside the lane where the SV can safely stop can be considered a suitable location.

[0083] Once the MRM-SS is activated, it automatically moves the vehicle to the appropriate position and stops the vehicle. The vehicle can optionally notify other vehicles or relevant road users of the emergency through radio communication or external devices on the SV.

[0084] The MRM-SS executed by the automated driving system (ADS) has the following functions.

[0085] 1. MRM-SS determines whether there is a potential stopping location (PSL) away from traffic where the vehicle can reach MRC. In the PSL, MRM-SS selects a target stopping location (TSL) where the vehicle will stop.

[0086] 2. When selecting a TSL from a PSL, MRM-SS can check whether the distance from the SV to the TSL is long enough to complete the MRM-SS, whether the state of the ADS is robust enough to reach the PSL safely, and whether there is available space at the PSL.

[0087] 3. MRM-SS safely controls the vehicle to a fixed location suitable for the target. This process may include changing lanes and / or crossing road boundaries.

[0088] 4. After MRM-SS completes vehicle maneuvering and the vehicle stops at TSL, ADS switches to parking management.

[0089] Upon receiving the MRM-SS trigger, the ADS with MRM-SS function immediately initiates the MRM-SS process. In addition to deceleration control, acceleration control is also allowed during driving to TSL.

[0090] Once the MRM-SS completes the vehicle maneuver and the vehicle stops at the TSL, the SV will be completely (full shoulder stop) or mostly (half shoulder stop) removed from the active lane.

[0091] Whether a lane boundary is crossed can be determined by MRM-SS, and there is no limit on the number of times a lane boundary is crossed. Lane changes are only made for the TSL expected by MRC.

[0092] When the MRM-SS detects that the driver has taken over control of the vehicle, it immediately transfers control to the driver.

[0093] Reference Figure 6 , the road on which the target vehicle (SV) travels may include a lane and / or a shoulder. The region of interest (ROI) is a region where the operation of the MRC to reach the SV is performed, and may contain an obstacle vehicle. Figure 6 An operation of moving a target vehicle (SV) from a lane in which the SV is traveling to a shoulder for parking by an MRM for shoulder parking according to an embodiment is shown. Hereinafter, the MRM for shoulder parking will be described with reference to each of the accompanying drawings. Specifically, an embodiment of entering a safe state by a control logic in an MRM-SS operation when the SV has difficulty reaching a target parking position (TSL) is described below.

[0094] Reference Figure 5 , the MRM type according to the embodiment includes types 1 to 3. The MRM method for shoulder parking according to the embodiment is MRM type 3.

[0095] Regarding MRM Type 3, Region of Interest (ROI) refers to "Vehicle Region of Interest", which is set based on data collected by on-board sensors of the vehicle, etc. It is determined based on the (horizontal / vertical) distance from the vehicle, lane, shoulder, road structure, road shape, etc. Potential Stopping Location (PSL) represents a suitable location (potential candidate location) for the vehicle to park safely away from traffic. The PSL can be generated by the MRM-SS function (MRM-SS Active). The ADS moves the vehicle out of the traffic flow and stops at the PSL on the shoulder outside the road lane.

[0096] The target parking position (TSL) indicates the position determined when the PSL satisfies the basic conditions of the MRM-SS. The vehicle performs the MRM-SS for the TSL and completes the MRM-SS when reaching the TSL. The ADS guides the vehicle to the TSL in the PSL.

[0097] Figure 7 Operation of a minimal risk maneuver for shoulder parking is shown in accordance with an embodiment.

[0098] Figure 7 It shows that Figure 6 An example of an operational workflow for MRM-SS is shown.

[0099] The MRM-SS process of ADS may include the following operations.

[0100] When the MRM-SS function receives an MRM trigger, MRM-SS will automatically switch to the active state immediately.

[0101] When MRM-SS is active, MRM-SS continues to monitor the ADS status. This monitoring involves sensors, controllers, brakes, and other components of the vehicle that are relevant to the ADS functionality. Monitoring also includes weather and traffic conditions. The status of the ADS is periodically transmitted to other MRM-SS components.

[0102] Generate a PSL list. Road information (e.g., road shape) or traffic information (e.g., traffic conditions on the shoulder) may form the basis for generating a PSL. Other relevant components of the SV (e.g., a map module or a V2X communication module) may be used to generate a PSL. The method of generating a PSL may depend on the manufacturer.

[0103] From a PSL perspective, it is best for the SV to park on the hard shoulder. However, when the shoulder is not available, any space outside the lane that allows the SV to park safely may serve as a suitable location. The PSL is the right (left) side of the road (shoulder).

[0104] TSL can be selected from PSL as shown below.

[0105] i) The MRM-SS function checks if there is enough free space at the PSL for the SV to park. This operation includes checking if there is enough physical space in the road geometry of the PSL and if the PSL is not physically occupied by other obstacles (e.g. other vehicles).

[0106] ii) The MRM-SS function checks if the PSL is within the ROI. This operation includes calculating the vertical distance and horizontal distance from the SV to the PSL. For the minimum distance to form the ROI, the distance from the SV to the TSL should be long enough to complete the MRM-SS. Considering the state of the ADS, the maximum distance to form the ROI is within the distance that the ADS can safely reach while continuing the MRM-SS control.

[0107] PSL can be considered as TSL when the following two conditions (i and ii) are met.

[0108] If no PSL satisfies both conditions (i and ii), the PSL generation process may be repeated or the ADS may switch to another type of MRM (e.g., MRM Type 1 for straight-ahead parking or MRM Type 2 for in-lane parking).

[0109] The MRM-SS function controls the SV to reach TSL. The ADS performs longitudinal and lateral control (including acceleration, deceleration, lane change, and road boundary violation).

[0110] During the MRM-SS control process, the ADS continuously checks whether the ADS is robust enough to reach the PSL. During the MRM-SS control process, if the ADS is no longer robust enough to continue the MRM-SS function, the PSL generation process can be repeated or the ADS can switch to another type of MRM (e.g., MRM Type 1 for straight-ahead parking or MRM Type 2 for in-lane parking).

[0111] When the SV successfully reaches the TSL, the MRM-SS process is completed.

[0112] When the MRM-SS function completes the MRM process after successfully reaching TSL, the ADS will switch to parking management.

[0113] When there is human intervention while the MRM-SS function is processing, the ADS will switch from MRM-SS to manual operation.

[0114] The specific method of selecting TSL in PSL may depend on the manufacturer. For example, TSL may be the PSL closest to SV.

[0115] refer to Figure 7 , a method for the ADS to perform MRM-SS may include: generating a first potential parking location (PSL), determining a target parking location (TSL) based on the first PSL, and controlling shoulder parking of the vehicle based on the TSL, wherein the determination of the TSL may include performing a first operation of MRM based on determining that the TSL is unsuccessful, wherein controlling shoulder parking of the vehicle may include performing a second operation of MRM based on determining that the TSL is difficult to reach.

[0116] In the TSL determination method, the MRM-SS function determines the TSL based on whether the PSL is within the ROI, whether the ADS is in a condition to reach the PSL, whether the PSL is available space, etc. In the TSL determination, if the MRM-SS does not have the conditions to determine the TSL, the ADS shall execute the subsequent safety control method. Next, refer to Figure 8 Describes the subsequent control method executed when the TSL determination condition is not satisfied.

[0117] Figure 8 Operation of a minimal risk maneuver for shoulder parking is shown in accordance with an embodiment.

[0118] Apart from Figure 7 In addition, Figure 8 A method of subsequent control of the MRM-SS is shown when the TSL determination condition (eg, whether the PSL is within the ROI, whether the ADS is in a condition to reach the PSL, whether the PSL is an available space, etc.) is not satisfied due to the TSL determination result.

[0119] In the PSL generation, the MRM-SS function generates the PSL before determining the TSL. In generating the PSL, at least one of the map information, the V2X information, and the vehicle-mounted sensing information may be referred to.

[0120] In TSL determination, the MRM-SS function determines whether the generated PSL is suitable for being determined as a TSL.

[0121] The MRM-SS function can determine that the PSL is the TSL when the following conditions are met: i) the PSL is within the ROI, ii) the vehicle can reach the PSL, and iii) there is available space at the PSL.

[0122] In TSL determination, in the case where TSL cannot be determined due to at least one of the above conditions not being met, a step of regenerating PSL may be performed in the default process ( Figure 8 800, ①). Because the time, vehicle position, or road conditions nearby are different from the time, vehicle position, or road conditions nearby given when the PSL was generated before the TSL was determined, a PSL different from the PSL initially generated may be generated. Figure 8 In 801, ②), the MRM type can be changed. Since the MRM type of MRM-SS is type 3, when the TSL of MRM-SS cannot be determined, the MRM type can be changed from type 3 to type 1 or 2. The operation of changing the MRM type does not include the option of regenerating the PSL.

[0123] The conditions for continuing the optional process according to the embodiment are as follows: Here, when the conditions for determining whether to continue the optional process are not satisfied, the MRM-SS function will execute the default process.

[0124] For example, when attempts to determine the TSL fail more than a threshold number of times after the PSL is generated, an optional process can be executed.

[0125] For example, when data received from a leading vehicle or infrastructure through vehicle-to-everything (V2X) (V2V, V2I) communication indicates that it is difficult to determine the TSL, the optional process can be performed. For example, the vehicle can receive information from a vehicle traveling in front of the vehicle on the same road through V2V communication that indicates that the TSL of the MRM-SS cannot be determined at a threshold number of times or more. In addition, the vehicle can receive information indicating the possibility of TSL determination of the MRM-SS from an infrastructure located in front of the vehicle through V2I communication. When the information indicates that the possibility of TSL determination is low, the optional process can be performed.

[0126] The method and apparatus for performing MRM-SS of a vehicle through an ADS according to an embodiment may determine whether the MRM-SS is sustainable.

[0127] like Figure 8 As shown, the above process can be used to determine TSL. When the generated PSL meets all the conditions for determining TSL, the PSL can be determined as TSL. After determining TSL, MRM-SS sustainability can be determined. That is, the ADS continuously checks whether the vehicle can reach TSL. When the ADS operates normally until the vehicle reaches TSL, the MRM-SS operation is completed after the vehicle reaches TSL.

[0128] However, when the method / apparatus for MRM-SS performed by ADS determines that MRM-SS is not sustainable (which is a result of MRM-SS sustainability determination), the following basic flow and / or additional flow is performed.

[0129] As a basic procedure, ADS can change the MRM type. It can change from MRM type 3 of MRM-SS to MRM type 1 or MRM type 2.

[0130] The additional process is performed together with the basic process. As an additional process, an alert (such as a message, an audible alert, etc.) may be sent to the driver to encourage the driver to take over.

[0131] When the vehicle traveling to TSL is in a situation where it is difficult to continue MRM-SS ( Figure 8802, No), at least one of the autonomous driving sensing, communication or control functions fails and the ADS faces an unstable situation. Therefore, an additional process is required. When the ADS is unstable, it may be safer to reduce the MRM type level from Type 3 to Type 1 or Type 2 and allow the driver to return to manual driving rather than continue to operate the autonomous driving MRM function. The alarm according to the embodiment can be provided by a message notification or a sound.

[0132] MRM-SS delivers a message notification and / or sound to the user to guide the driver to take over when the determination is "No" ( Figure 8 802 in the figure). According to the embodiment, the message notification / sound may be sent to the user device (smartphone) or the vehicle DVD navigation host (Audio, Video, Navigation, AVN). On the user device / vehicle AVN, the message may be displayed or implemented in a manner including "text with details of guiding takeover" and "graphical icon (GUI) for selecting takeover" and / or sound notification.

[0133] exist Figure 8 In the method and apparatus for performing MRM-SS according to an embodiment, the level of the MRM type may be changed based on a default procedure and / or an optional procedure as follows.

[0134] As a default process, the MRM type can be changed from MRM-SS (Type 3) to Type 2 (Level). When it is difficult to reach TSL using MRM Type 3, changing the MRM level to Type 2 as the default method is necessary, which has less impact on the traffic flow between Type 1 and / or Type 2. Specifically, Type 2 stops the vehicle while maintaining the driving lane, so it is necessary to identify the driving lane. If access to one of the communication module / sensing module / database is available, lane recognition is available, so changing the level to Type 2 is appropriate in most cases.

[0135] As an optional process, the MRM type can be changed from MRM-SS (Type 3) to Type 1 (Level). When access to the communication module / sensing module / database is not available, lane recognition may not be allowed, and attempting to change the level to Type 2 may be an unnecessary waste of time. In an emergency situation when access to the communication module / sensing module / database is not available, it may be appropriate to attempt to immediately change the level to Type 1. Specifically, a) the vehicle's ADS can receive information from each module indicating whether the module has failed. b) Determination: After receiving information indicating a failure of each module from the communication module / sensing module / database, the MRM-SS function can immediately attempt to change the level to Type 1.

[0136] Fig. 9A method for minimal risk maneuvering for shoulder parking according to an embodiment is shown.

[0137] Fig. 9 Shows the Figure 1 ADS Figure 4 Vehicle control device 4000 or Figure 5 Vehicles targeting Figure 2 MRM and Figure 3 MRM-SS control, MRM type change, MRM-SS continuity determination, and how to Figures 6 to 8 A flowchart of the process of subsequent operations is shown.

[0138] S900: The MRM method according to the embodiment may include generating a first potential parking location (PSL). For the generation of the PSL according to the embodiment, please refer to Figure 7 and Figure 8 Description.

[0139] S901: The MRM method according to the embodiment may further include determining a target parking location (TSL) based on the first PSL. For a method for determining the TSL according to the embodiment, please refer to Figure 7 and Figure 8 Description.

[0140] S902: The MRM method according to the embodiment may further include controlling the vehicle to park on a shoulder based on the TSL. For the operation of controlling the vehicle to park on a shoulder according to the embodiment, please refer to Figure 7 and Figure 8 Description.

[0141] The MRM method according to an embodiment may include: performing a control operation to reach a stop state when a TSL determination or maintenance condition is not satisfied, performing subsequent control operations to determine the TSL based on a result of the TSL determination, performing subsequent control operations when the TSL maintenance condition is not satisfied even after the TSL determination, and also including adjusting the MRM type level.

[0142] refer to Figure 7 , a method for the ADS to perform MRM-SS may include: generating a first potential parking location (PSL), determining a target parking location (TSL) based on the first PSL, and controlling shoulder parking of the vehicle based on the TSL, wherein determining the TSL may include performing a first operation of MRM based on determining that the TSL is unsuccessful, wherein controlling shoulder parking of the vehicle may include performing a second operation of MRM based on determining that the TSL is difficult to reach.

[0143] about Figure 8In 800 and 801, the first operation is to generate a second PSL different from the first PSL or change the MRM type, wherein the MRM type may be one of MRM type 1 for through parking, MRM type 2 for in-lane parking, or MRM type 3 for shoulder parking. Changing the MRM type may include changing the MRM type from MRM type 3 to one of MRM type 1 and MRM type 2.

[0144] In addition, changing the MRM type may include: changing the MRM type from MRM type 3 to MRM type 2 based on at least one of the ADS communication module, sensing module or database being in a normal state, and changing the MRM type from MRM type 3 to MRM type 1 based on the ADS communication module, sensing module and database being in an abnormal state.

[0145] The first operation may further include generating a second PSL based on that the preset condition is not satisfied, and changing the MRM type based on that the preset condition is satisfied.

[0146] The preset conditions may include: i) a condition that the number of unsuccessful determinations of TSL is greater than or equal to a threshold number, or ii) a condition that data received from a preceding vehicle or infrastructure through vehicle-to-everything (V2X) communication indicates that it is difficult to determine TSL.

[0147] In addition, the second operation may be to change the MRM type, and the MRM type may be one of MRM type 1 for straight parking, MRM type 2 for parking in a lane, or MRM type 3 for shoulder parking. The change of the MRM type may include: changing the MRM type from MRM type 3 to one of MRM type 1 and MRM type 2. Here, the second operation does not include an option to regenerate the PSL.

[0148] In addition, changing the MRM type may include: changing the MRM type from MRM type 3 to MRM type 2 based on that at least one of the communication module, sensing module or database of ADS is in a normal state, and changing the MRM type from MRM type 3 to MRM type 1 based on that the communication module, sensing module and database of ADS are in an abnormal state.

[0149] Furthermore, controlling the shoulder parking of the vehicle may include performing a second operation and a takeover alarm based on determining that the TSL is difficult to reach, wherein the takeover alarm is at least one of a message alarm or an audible alarm to guide the vehicle driver to take over.

[0150] A method for executing MRM-SS of a vehicle by an automated driving system (ADS), performed by the ADS for executing MRM-SS of the vehicle. The ADS can control and execute Figure 1 Pictures, Figure 2 MRM Figure 3 The MRM type and can correspond to Figure 4 equipment, Figure 5 The ADS may include a transceiver, a memory, and a processor. The processor may be configured to perform operations including generating a potential parking location (PSL), determining a target parking location (TSL) based on the PSL, and controlling a shoulder parking of the vehicle based on the TSL. Determining the TSL may include performing a first operation of the MRM based on determining that the TSL is unsuccessful, and controlling the shoulder parking of the vehicle may include performing a second operation of the MRM based on determining that the TSL is difficult to reach.

[0151] Therefore, when the SV cannot reach TSL or cannot maintain TSL after reaching TSL, the SV performing the MRM-SS operation can safely and effectively perform MRM-SS. In addition, when the SV cannot perform MRM-SS, it can effectively perform safe subsequent control.

[0152] The embodiments have been described in terms of methods and / or devices. The description of the method and the description of the device may complement each other.

[0153] Although the embodiments have been described with reference to each of the accompanying drawings for simplicity, new embodiments can be designed by combining the embodiments shown in the accompanying drawings. If a person skilled in the art designs a computer-readable recording medium (in which a program for executing the embodiments mentioned in the above description is recorded), it may also fall within the scope of the technical solutions of the attached present disclosure and their equivalents. The device and method may not be limited by the configuration and method of the above-mentioned embodiments. The above-mentioned embodiments may be configured by selectively combining them in whole or in part with each other to achieve various modifications. Although the preferred embodiments have been described with reference to the accompanying drawings, it will be understood by those skilled in the art that various modifications and changes may be made to the embodiments without departing from the spirit or scope of the disclosure described in the technical solutions of the attached present disclosure. Such modifications cannot be understood separately from the technical ideas or perspectives of the embodiments.

[0154] Various elements of the device of the embodiment can be implemented by hardware, software, firmware or a combination thereof. Various elements in the embodiment can be implemented by a single chip (e.g., a single hardware circuit). According to an embodiment, the components according to the embodiment can be implemented as separate chips respectively. According to an embodiment, at least one or more components of the components of the device according to the embodiment may include one or more processors capable of executing one or more programs. One or more programs may execute any one or more of the operations / methods according to the embodiment, or include instructions for executing them. The executable instructions for executing the method / operation of the device according to the embodiment may be stored in a non-temporary computer readable medium (computerreadable medium, CRM) or other computer program products configured to be executed by one or more processors, or may be stored in a temporary CRM or other computer program products configured to be executed by one or more processors. In addition, the memory according to the embodiment can be used as a concept that not only covers volatile memory (e.g., random access memory (RandomAccess Memory, RAM)) but also covers non-volatile memory, flash memory and programmable read-only memory (programmableread-only memory, PROM). In addition, it can also be implemented in the form of a carrier wave (e.g., transmitted over the Internet). Furthermore, the processor-readable recording medium can be distributed to computer systems connected through a network so that processor-readable codes can be stored and executed in a distributed manner.

[0155] In this document, the terms " / " and "," should be interpreted as meaning "and / or". For example, the expression "A / B" may mean "A and / or B". Furthermore, "A, B" may mean "A and / or B". Furthermore, "A / B / C" may mean "at least one of A, B, and / or C". "A, B, C" may mean "at least one of A, B, and / or C". Furthermore, in this document, the term "or" should be interpreted as "and / or". For example, the expression "A or B" may mean: 1) only A, 2) only B, and / or 3) A and B. In other words, the term "or" in this document should be interpreted as "additionally or alternatively".

[0156] Terms such as first and second can be used to describe various elements of the embodiments. However, various components according to the embodiments should not be limited by the above terms. These terms are only used to distinguish one element from another. For example, a first user input signal can be referred to as a second user input signal. Similarly, a second user input signal can be referred to as a first user input signal. The use of these terms should be interpreted as not departing from the scope of various embodiments. The first user input signal and the second user input signal are both user input signals, but unless the context clearly indicates otherwise, it does not mean the same user input signal.

[0157] The terms used to describe the embodiments are only used to describe specific embodiments and are not intended to limit the embodiments. As used in the description of the embodiments and the technical solutions of the present disclosure, unless the context clearly indicates otherwise, the singular forms "one", "one", "said" include multiple plural indicators. The expression "and / or" is used to include all possible combinations of terms. Terms such as "including" or "having" are intended to represent the presence of graphics, numbers, steps, elements and / or parts, and should be understood as not excluding the possibility of the presence of additional graphics, numbers, steps, elements and / or parts. Conditional expressions (such as "if" and "when") as used herein are not limited to optional situations, but are intended to explain that when certain conditions are met, relevant operations are performed or relevant definitions are explained according to certain conditions.

[0158] The operations according to the embodiments described in this specification may be performed by a sending / receiving device including a memory and / or a processor according to the embodiments. The memory may store a program for processing / controlling the operations according to the embodiments, and the processor may control the various operations described in this specification. The processor may be referred to as a controller, etc. In an embodiment, the operations may be performed by firmware, software, and / or a combination thereof. The firmware, software, and / or a combination thereof may be stored in a processor or a memory.

[0159] The operations according to the above-described embodiments may be performed by a sending device and / or a receiving device according to the embodiments. The sending / receiving device may include: a transmitter / receiver configured to send and receive media data; a memory configured to store instructions (program code, algorithm, flow chart and / or data) for processing according to the embodiments; and a processor configured to control the operation of the sending / receiving device.

[0160] The processor may be referred to as a controller, etc., and may correspond to, for example, hardware, software, and / or a combination thereof. The operations according to the above-described embodiments may be performed by a processor.

[0161] As described above, relevant details have been described in the best mode for carrying out the embodiment.

[0162] As described above, the embodiments are fully or partially applicable to methods, devices and systems for MRM.

[0163] Those skilled in the art can change or modify the embodiments in various ways within the scope of the embodiments.

[0164] The embodiments may include changes / modifications within the scope of the technical solutions of the present disclosure and their equivalents.

Claims

1. A method for performing a minimum risk maneuver (MRM) for autonomous driving of a vehicle (Stop on a Roadside) by an autonomous driving system (ADS), the method comprising: generating a first potential parking location PSL; determining a target parking position TSL based on the first potential parking position PSL; as well as Based on the target parking position TSL, the vehicle is controlled to park on the shoulder of the road. Determining the target parking position TSL includes: Based on determining that the target parking position TSL is unsuccessful, performing a first operation of a minimum risk maneuver MRM, Wherein, controlling the vehicle to park on the shoulder includes: Based on determining that it is difficult to reach the target parking position TSL, a second operation of the minimum risk maneuver MRM is performed.

2. The method according to claim 1, wherein: The first operation is to generate a second potential parking position PSL different from the first potential parking position PSL or to change the MRM type. wherein the MRM type is one of MRM type 1 for through parking, MRM type 2 for in-lane parking, or MRM type 3 for shoulder parking, Wherein said changing the MRM type comprises: The MRM type is changed from the MRM type 3 to one of the MRM type 1 and the MRM type 2.

3. The method according to claim 2, wherein: The changing MRM type includes: Based on at least one of the communication module, the sensing module, and the database of the ADS being in a normal state, changing the MRM type from the MRM type 3 to the MRM type 2; and The MRM type is changed from the MRM type 3 to the MRM type 1 based on the communication module, the sensing module, and the database of the ADS being in an abnormal state.

4. The method according to claim 3, wherein: The first operation includes: generating the second potential parking location PSL based on the preset condition not being satisfied; and The MRM type is changed based on a preset condition being met.

5. The method according to claim 4, wherein: The preset conditions include: Determine the condition that the number of unsuccessful TSLs of the target parking position is greater than or equal to a threshold number; or Data received from a preceding vehicle or infrastructure via vehicle-to-everything (V2X) communication indicates conditions where it is difficult to determine the target parking location TSL.

6. The method according to claim 1, wherein: The second operation is to change the MRM type, wherein the MRM type is one of MRM type 1 for through parking, MRM type 2 for in-lane parking, or MRM type 3 for shoulder parking, Wherein said changing the MRM type comprises: The MRM type is changed from the MRM type 3 to one of the MRM type 1 and the MRM type 2.

7. The method according to claim 6, wherein: The changing MRM type includes: Based on at least one of the communication module, the sensing module, and the database of the ADS being in a normal state, changing the MRM type from the MRM type 3 to the MRM type 2; and The MRM type is changed from the MRM type 3 to the MRM type 1 based on the communication module, the sensing module, and the database of the ADS being in an abnormal state.

8. The method according to claim 6, wherein: Controlling the vehicle's shoulder parking includes: performing the second operation and taking over the alarm based on determining that the target parking position TSL is difficult to reach, The takeover alarm is at least one of a message alarm or a sound alarm for guiding the driver of the vehicle to take over.

9. An automated driving system (ADS) for performing an automated minimum risk maneuver (MRM)-shoulder stop (SS) of a vehicle, the automated driving system (ADS) comprising: Transceiver; Memory; and one or more processors; The one or more processors are configured to perform operations, the operations comprising: Generate potential parking location PSL; Based on the potential parking position PSL, determining a target parking position TSL; and Based on the target parking position TSL, the vehicle is controlled to park on the shoulder of the road. The determining of the target parking position TSL comprises: performing a first operation for a minimum risk maneuver MRM based on determining that the target parking position TSL is unsuccessful, Wherein, the control of the vehicle's shoulder parking includes: Based on determining that the target parking position TSL is difficult to reach, a second operation for the minimum risk maneuver MRM is performed.

Images