Method and system for takeover of automated driving assistance by a driver under external threat

Abstract

According to an exemplary embodiment, a method and system for controlling the steering of an autonomous vehicle are provided. The method includes: operating the autonomous vehicle by a processor in a path-based automated driving assistance mode; receiving a driver input including a driver torque by the processor; classifying the operating mode by the processor according to a type of path-based automated driving assistance mode; determining, based on the operating mode, a takeover threshold for taking over the path-based automated driving assistance mode on a first side of the autonomous vehicle; determining a driver takeover state by the processor based on the takeover torque threshold; and generating a control signal by the processor based on the driver takeover state and the driver torque to control the steering of the autonomous vehicle.

Description

Technical Field

[0001] This invention relates generally to vehicles, and more specifically to methods and systems for driver overriding path-based autonomous driving assistance in the presence of external threats. Background Technology

[0002] Path-based automated driving assistance features enable automatic lane keeping and / or lane following via steering control. While automatic steering control is in progress, the driver should be able to take over control at any time. When the driver takes over control, for example, in the presence of an external threat, a natural driver takeover feel is desirable. Consistency in the driver takeover feel across various automated driving assistance features, such as lane keeping assist, side collision avoidance, and manual lane centering, is also desirable.

[0003] Therefore, it is desirable to provide a method and system for driver takeover of path-based autonomous driving assistance in the presence of external threats. Furthermore, other desirable features and characteristics of the invention will become apparent from the following detailed description and appended claims, taken in conjunction with the accompanying drawings and the foregoing technical and background information. Summary of the Invention

[0004] According to an exemplary embodiment, a method and system for controlling the steering of an autonomous vehicle are provided. The method includes: operating the autonomous vehicle by a processor in a path-based automated driving assistance mode; receiving a driver input including a driver torque by the processor; classifying the operating mode by the processor according to a type of path-based automated driving assistance mode; determining, based on the operating mode, a takeover threshold for taking over the path-based automated driving assistance mode on a first side of the autonomous vehicle; determining a driver takeover state by the processor based on the takeover torque threshold; and generating a control signal by the processor based on the driver takeover state and the driver torque to control the steering of the autonomous vehicle.

[0005] In various embodiments, the path-based autonomous driving assistance modes include at least one of lane keeping assist mode, side collision avoidance mode, and manual lane centering mode.

[0006] In various embodiments, the method includes determining a safety barrier takeover threshold in response to detecting the presence of a safety barrier on the side of an autonomous vehicle, and the determination of the takeover threshold is further based on the safety barrier takeover threshold.

[0007] In various embodiments, the safety barrier takeover threshold is determined based on the classification of the safety barrier and the barrier dynamics between the autonomous vehicle and the safety barrier.

[0008] In various embodiments, the barrier dynamics include collision time and the relative speed between the autonomous vehicle and the safety barrier.

[0009] In various embodiments, the classification of security barriers is based on the type of security barrier and the severity of barrier intrusion.

[0010] In various embodiments, the takeover threshold is determined based on steady-state steering torque associated with lane curvature, vehicle parameters, and external disturbances.

[0011] In various embodiments, external disturbances include at least one of road angle, road friction, and crosswinds.

[0012] In various embodiments, vehicle parameters include at least one of vehicle speed, vehicle inertia, and vehicle mass.

[0013] In various embodiments, determining the driver takeover state is also based on the magnitude and direction of the controller torque, the magnitude and direction of the driver torque, and the direction of the steering switch.

[0014] In another embodiment, a system for controlling the steering of an autonomous vehicle is provided. The system includes a non-transitory computer-readable medium comprising computer instructions configured to perform a process; and a processor configured to perform the process. The process includes: operating the autonomous vehicle in a path-based automated driving assistance mode by the processor; receiving driver input including driver torque by the processor; classifying the operating mode according to the type of the path-based automated driving assistance mode by the processor; determining a takeover threshold for taking over the path-based automated driving assistance mode on a first side of the autonomous vehicle based on the operating mode; determining a driver takeover state by the processor based on the takeover threshold; and generating a control signal to control the steering of the autonomous vehicle based on the driver takeover state and driver torque by the processor.

[0015] In various embodiments, the path-based autonomous driving assistance modes include at least one of lane keeping assist mode, side collision avoidance mode, and manual lane centering mode.

[0016] In various embodiments, the process further includes determining a safety barrier takeover threshold in response to detecting the presence of a safety barrier on the side of the autonomous vehicle, and the determination of the takeover threshold is also based on the safety barrier takeover threshold.

[0017] In various embodiments, the safety barrier takeover threshold is determined based on the classification of the safety barrier and the barrier dynamics between the autonomous vehicle and the safety barrier.

[0018] In various embodiments, barrier dynamics include collision time and the relative speed between the autonomous vehicle and the safety barrier.

[0019] In various embodiments, the classification of security barriers is based on the type of security barrier and the severity of barrier intrusion.

[0020] In various embodiments, the takeover threshold is determined based on steady-state steering torque associated with lane curvature, vehicle parameters, and external disturbances.

[0021] In various embodiments, external disturbances include at least one of road angle, road friction, and crosswinds.

[0022] In various embodiments, vehicle parameters include at least one of vehicle speed, vehicle inertia, and vehicle mass.

[0023] In various embodiments, determining the driver takeover state is also based on the magnitude and direction of the controller torque, the magnitude and direction of the driver torque, and the direction of the steering switch. Attached Figure Description

[0024] The present disclosure will be described below in conjunction with the accompanying drawings, wherein like reference numerals denote like elements, wherein:

[0025] Figure 1 This is a functional block diagram of an autonomous vehicle including a driver takeover system according to an exemplary embodiment;

[0026] Figure 2 This is a functional block diagram of an autonomous driving system for an autonomous vehicle, including a driver takeover system, according to various embodiments.

[0027] Figure 3 This is a data flow diagram illustrating a driver takeover system according to an exemplary embodiment;

[0028] Figure 4 This is a diagram illustrating the driver takeover logic and logical relationships of a driver takeover system according to an exemplary embodiment;

[0029] Figure 5 This is a dynamic illustration of a safety barrier used by a driver takeover system according to an exemplary embodiment;

[0030] Figure 6 It is a graph showing the steady-state torque value used by the driver takeover system according to an exemplary embodiment;

[0031] Figure 7 This is a flowchart of a process for providing driver takeover functionality to control the steering of an autonomous vehicle, according to an exemplary embodiment. Detailed Implementation

[0032] The following detailed description is exemplary in nature only and is not intended to limit this disclosure or its application and use. Furthermore, it is not intended to be bound by any theory set forth in the foregoing background or the following detailed description. Embodiments of this disclosure can be described herein according to functional and / or logical block components and various processing steps. It should be understood that such block components can be implemented by any number of hardware, software, and / or firmware components configured to perform specified functions. For example, embodiments of this disclosure can employ various integrated circuit components, such as memory elements, digital signal processing elements, logic elements, lookup tables, etc., which can perform various functions under the control of one or more microprocessors or other control devices. Furthermore, those skilled in the art will understand that embodiments of this disclosure can be practiced in conjunction with any number of systems, and the systems described herein are merely exemplary embodiments of this disclosure.

[0033] For the sake of brevity, conventional techniques related to signal processing, data transmission, signaling, control, and other functional aspects of the system (as well as the various operating components of the system) may not be described in detail herein. Furthermore, the connecting lines shown in the various figures contained herein are intended to represent exemplary functional relationships and / or physical couplings between the various elements. It should be noted that many alternative or additional functional relationships or physical connections may exist in the embodiments of this disclosure.

[0034] refer to Figure 1 According to various embodiments, a driver takeover system, generally shown as 100, is associated with vehicle 10. Typically, driver takeover system 100 allows the driver to take over the automatic steering control of vehicle 10 in a safe and natural manner. In various embodiments, driver takeover system 100 provides methods and systems for efficiently determining driver takeover thresholds to provide a natural driver takeover experience. For example, driver takeover system 100 independently evaluates the takeover threshold on each of the left and right sides of vehicle 10, and in various embodiments, adaptively modifies the takeover threshold based on safety barrier classification. In various embodiments, driver takeover system 100 unifies the takeover strategy for different driver assistance operating modes.

[0035] like Figure 1 As shown, vehicle 10 typically includes a chassis 12, a body 14, front wheels 16, and rear wheels 18. The body 14 is mounted on the chassis 12 and substantially surrounds the components of vehicle 10. The body 14 and chassis 12 may together form a frame. The wheels 16-18 are each rotatably connected to the chassis 12 near a corresponding corner of the body 14.

[0036] In various embodiments, vehicle 10 is an autonomous vehicle, and driver takeover system 100 is integrated into autonomous vehicle 10. Autonomous vehicle 10 is, for example, a vehicle automatically controlled to transport passengers from one location to another. In the illustrated embodiment, vehicle 10 is described as a passenger car; however, it should be understood that any other vehicle, including motorcycles, trucks, SUVs, RVs, ships, aircraft, etc., may also be used. In exemplary embodiments, autonomous vehicle 10 is so-called Level 2 or Level 3 automation. It will be understood that in various embodiments, autonomous vehicle 10 can be any level of automation.

[0037] As shown in the figure, an autonomous vehicle 10 typically includes a propulsion system 20, a drivetrain 22, a steering system 24, a braking system 26, a sensor system 28, an actuator system 30, at least one data storage device 32, at least one controller 34, and a communication system 36. In various embodiments, the propulsion system 20 may include an internal combustion engine, an electric motor (such as a traction motor), and / or a fuel cell propulsion system. The drivetrain 22 is configured to transmit power from the propulsion system 20 to the wheels 16-18 according to a selectable speed ratio. According to various embodiments, the drivetrain 22 may include a stepped automatic transmission, a continuously variable transmission (CVT), or other suitable transmission. The braking system 26 is configured to provide braking torque to the wheels 16-18. In various embodiments, the braking system 26 may include friction brakes, line brakes, regenerative braking systems (such as electric motors), and / or other suitable braking systems. The steering system 24 influences the position of the wheels 16-18.

[0038] Sensor system 28 includes one or more sensing devices 40a-40n that sense observable conditions of the external and / or internal environment of autonomous vehicle 10. Sensing devices 40a-40n may include, but are not limited to, radar, lidar, global positioning system, optical camera, thermal camera, ultrasonic sensor, inertial measurement unit, and / or other sensors. In various embodiments, sensing devices 40a-40n include one or more image sensors that generate image sensor data used by system 100.

[0039] The actuator system 30 includes one or more actuator devices 42a-42n that control one or more vehicle features, such as, but not limited to, the propulsion system 20, the transmission system 22, the steering system 24, and the braking system 26. In various embodiments, the vehicle features may further include interior and / or exterior vehicle features, such as, but not limited to, doors, trunk, and cabin features, such as air, music, lighting, etc. (not numbered).

[0040] Communication system 36 is configured to wirelessly transmit information to and from other entities 48, such as, but not limited to, other vehicles (“V2V” communication), infrastructure (“V2I” communication), remote systems and / or personal devices (regarding...). Figure 2 (Described in more detail). In an exemplary embodiment, communication system 36 is a wireless communication system configured to communicate via a wireless local area network (WLAN) using the IEEE 802.11 standard or by using cellular data communication. However, additional or alternative communication methods, such as dedicated short-range communication (DSRC) channels, are also considered to be within the scope of this disclosure. A DSRC channel refers to a one-way or two-way short-to-medium-range wireless communication channel specifically designed for automotive applications, along with a corresponding set of protocols and standards.

[0041] Data storage device 32 stores data used for automatically controlling the autonomous vehicle 10. In various embodiments, data storage device 32 stores a defined map of the navigable environment. In various embodiments, the defined map may be predefined by a remote system and obtained from the remote system (see reference). Figure 2 (Further detailed description follows). For example, the definition map may be assembled by a remote system and transmitted to the autonomous vehicle 10 (wirelessly and / or via wire) and stored in data storage device 32. In various embodiments, the definition map includes an elevation map of the environment used by system 100. It is understood that data storage device 32 may be part of controller 34, separate from controller 34, or part of controller 34 and a separate system.

[0042] The controller 34 includes at least one processor 44 and a computer-readable storage device or medium 46. The processor 44 can be any custom or commercially available processor, central processing unit (CPU), graphics processing unit (GPU), auxiliary processor among several processors associated with the controller 34, semiconductor-based microprocessor (in the form of a microchip or chipset), macroprocessor, any combination thereof, or any device generally used for executing instructions. The computer-readable storage device or medium 46 can include volatile and non-volatile storage, such as read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM). KAM is a permanent or non-volatile memory that can be used to store various operational variables when the processor 44 is powered off. The computer-readable storage device or medium 46 can be implemented using any of a variety of known storage devices, such as PROM (programmable read-only memory), ePROM (electrical PROM), EEPROM (electrically erasable PROM), flash memory, or any other electrical, magnetic, optical, or combined storage device capable of storing data, some of which represents executable instructions used by the controller 34 in controlling the autonomous vehicle 10.

[0043] The instructions may include one or more separate programs, each comprising an ordered list of executable instructions for implementing logical functions. When executed by processor 44, these instructions receive and process signals from sensor system 28, execute logic, calculations, methods, and / or algorithms for automatically controlling components of autonomous vehicle 10, and generate control signals to actuator system 30 to automatically control components of autonomous vehicle 10 based on that logic, calculations, methods, and / or algorithms. Although in Figure 1 Only one controller 34 is shown, but embodiments of the autonomous vehicle 10 may include any number of controllers 34 that communicate via any suitable communication medium or combination of communication media and cooperate to process sensor signals, execute logic, calculations, methods and / or algorithms, and generate control signals to automatically control the features of the autonomous vehicle 10.

[0044] In various embodiments, one or more instructions of the controller 34 are included in the driver takeover system 100, and when executed by the processor 44, data from sensors and / or data from within the controller are processed to determine a driver takeover threshold, and the driver takeover threshold is used to determine a driver takeover state that indicates whether the steering of the vehicle 10 should be controlled using driver input or autonomous control.

[0045] According to various embodiments, the controller 34 is implemented as follows: Figure 2 The illustrated Automated Driving System (ADS) 70. That is, suitable software and / or hardware components of the controller 34 (e.g., processor 44 and computer-readable storage device 46) are used to provide the Automated Driving System 70 for use in conjunction with the vehicle 10.

[0046] In various embodiments, the instructions of the autonomous driving system 70 can be organized by function, module, or system. For example, as Figure 2 As shown, the autonomous driving system 70 may include a computer vision system 74, a positioning system 76, a guidance system 78, and a vehicle control system 80. As will be understood, in various embodiments, instructions may be organized into any number of systems (e.g., combined, further divided, etc.), as this disclosure is not limited to the present example.

[0047] In various embodiments, the computer vision system 74 synthesizes and processes sensor data and predicts the presence, location, classification, and / or path of objects and features in the environment of the vehicle 10. In various embodiments, the computer vision system 74 may combine information from multiple sensors, including but not limited to cameras, lidar, radar, and / or any number of other types of sensors.

[0048] The positioning system 76 processes sensor data and other data to determine the position of the vehicle 10 (e.g., local position relative to a map, precise position relative to a road lane, vehicle heading, speed, etc.) relative to changes in the environment. The guidance system 78 processes sensor data and other data to determine the path that the vehicle 10 should follow. The vehicle control system 80 generates control signals for controlling the vehicle 10 based on the determined path.

[0049] In various embodiments, the controller 34 implements machine learning techniques to assist the functions of the controller 34, such as feature detection / classification, obstacle mitigation, route traversal, mapping, sensor integration, and ground condition determination.

[0050] As briefly described above, Figure 1 The driver takeover system 100 may be wholly or partially included within the ADS 70, for example, as part of the guidance system 78 and / or the vehicle control system 80. For example, the driver takeover system 100 generates data indicating the takeover status of the guidance system 78, enabling the guidance system 78 to communicate to the vehicle control system 80 whether the autonomous function is controlling the steering or whether the driver input is controlling the steering.

[0051] For example, such as regarding Figure 3 And continue to refer to Figure 1 and 2 As shown in more detail, the driver takeover system 100 includes an operating mode determination module 102, a safety barrier takeover module 104, a takeover threshold determination module 106, a unified takeover logic module 108, and a calibration data storage 110.

[0052] The operation mode determination module 102 receives function mode data 112 and threat data 114 as input. The operation mode determination module 102 classifies the operation modes (M) and generates operation mode data 116 based on the type of activated driver assistance function mode indicated by the function mode data 112, and further based on the detected threats indicated by the threat data 114. For example, the driver assistance function mode may be, but is not limited to: side collision avoidance mode, lane keeping assist mode, or manual lane centering assist mode. Threat detection may indicate whether a threat is detected on the left or right side of the vehicle 10.

[0053] In various embodiments, such as Figure 4As shown, the operation mode determination module 102 classifies the operation mode (M) 202 based on scenario 201 into one of the following: Left Collision Avoidance Mode (LLIA), Left Lane Keeping Assist Mode (LLKA), Lane Centering Assist Left Threat Mode (CLT), Lane Centering Assist Mode (CNT), Lane Centering Assist Right Threat Mode (CRT), Right Lane Keeping Assist Mode (RLKA), and Right Collision Avoidance Mode (RLIA). As shown in the figure, each mode is determined by the direction of the steering switch (I). d )204, Threat side (S)206 and driver torque direction (Dτd)208 are defined.

[0054] Return to reference Figure 3 The safety barrier takeover module 104 receives safety barrier data 118. The safety barrier takeover module 104 independently detects the presence of a safety barrier on each side of the vehicle 10 and classifies the safety barriers according to their classification (G). Bar Adaptively modify the corresponding security barrier takeover threshold (G) SB For example, the security barrier takeover threshold (G). SB Increase the threshold near security barriers classified as less critical, and further increase it near security barriers classified as critical. The security barrier takeover module 104 generates an indication security barrier threshold (G). SB The security barrier takeover threshold data is 120.

[0055] In various embodiments, the classification of safety barriers (G) Bar It can be based on the barrier dynamics (G) BarDyn ) and barrier category (G BarClass To determine. For example, such as Figure 5 As shown, barrier dynamics (G BarDyn The time to impact (t) is determined by the dynamics between vehicle 502 and safety barrier 504, such as the time to impact. TTI The relative speed (ΔV) between vehicle 502 and safety barrier 504. In another example, the barrier category (G) is identified based on the type of safety barrier 504 and the severity of barrier intrusion. BarClass The severity of barrier intrusion depends on the type of vehicle (e.g., car, bus, semi-truck, construction vehicle, etc.), the type of lane markings (e.g., dashed lines, solid lines, double lines, etc.), and the identified object or landmark (e.g., sign, building, geography, etc.).

[0056] Return to reference Figure 3The takeover threshold determination module 106 receives safety barrier takeover threshold data 120, function mode data 112, vehicle parameter data 122, and external interference data 124. The takeover threshold determination module 106 determines the optimal takeover threshold and generates takeover threshold data 130 using vehicle-specific and mathematically based data. This mathematically based data provides a natural driver takeover experience and consistent performance across different vehicle applications.

[0057] For example, calibration data memory 110 stores calibration data, such as Figure 6 As shown, the calibration data characterizes the steady-state driver steering torque 604, which follows the curvature 602 as vehicle parameters change, such as speed (37 mph, 52 mph, and 67 mph) and disturbances (e.g., crosswind, road slope angle, road friction, etc.). The required steering torque can be obtained from empirical or analytical data, such as vehicle testing or engineering calculations. The takeover threshold determination module 106 sets a takeover threshold to closely match the steady-state steering torque τ required to track the target path curvature under measured vehicle parameters and external disturbances. ss To achieve the optimal takeover threshold. This provides a natural driver takeover feel during takeover maneuvers on winding roads without safety barriers. The safety barrier threshold serves as a modifier to the takeover threshold to increase the difficulty of a takeover maneuver that would result in a collision between the vehicle and the safety barrier. Additional driver takeover attempts prevent the driver from unintentionally taking over driver assistance functions.

[0058] Return to reference Figure 3 The unified takeover logic module 108 receives operating mode data 116, takeover threshold data 130, driver input data 132, and controller input data 134. The unified takeover logic module 108 is based on the operating mode (M), takeover threshold (G), threat side (S), and driver input (i.e., steering switch direction I). D Driver's steering torque magnitude τ D and direction ) and controller inputs (i.e., the magnitude τ and direction D of the controller steering torque) τ The takeover status flag (O) is calculated and takeover flag data 136 is generated. For example, in unified takeover logic, lateral driver inputs such as steering switch and steering torque can activate the takeover status flag. In the absence of lateral threat, discrete and invariant driver inputs (e.g., steering switch activation) can set the takeover status flag on the indicated side. Steering switch direction (I DThe driver input is compared with the threat side (S) to determine whether the steering switch indication direction allows takeover. If the driver input reaches or exceeds the takeover threshold (G) in the takeover threshold data 130, continuous and varying driver input (e.g., steering torque) can set the takeover status flag (O) in the presence of a lateral threat. To determine the driver takeover direction, the driver steering torque (τ) is compared with the threat side (S) to determine whether the takeover is permitted. D ) and direction With the controller's steering torque (τ) and direction (D) τ The comparison is performed. If the driver input reaches or exceeds the takeover threshold (G) in the takeover direction, the takeover status flag (O) is set.

[0059] Figure 7 This is a flowchart of a process 700 for determining a driver takeover state according to an exemplary embodiment. According to the exemplary embodiment, process 700 can be combined with... Figure 1 Vehicle 10 Figure 2 ADS 70 and Figure 3 The driver takeover system 100 is used for implementation. As can be understood from this disclosure, the sequence of operations within process 700 is not limited to... Figure 7 The process 700 may be executed in the order shown, but can be executed in one or more different orders applicable and according to this disclosure. In various embodiments, process 700 may be scheduled to run based on one or more predetermined events, and / or may run continuously during operation of vehicle 10.

[0060] like Figure 7 As shown, process 700 can begin at 702. At 704, for each side of vehicle 10, the takeover state is determined at 706-712. For example, at 706, the operating mode (M) is determined based on the functional mode and the detected threat. At 708, the security barrier threshold (GSB) is determined based on barrier dynamics and barrier type. At 710, the takeover state is determined in part based on the security barrier threshold (G). SB The takeover threshold is then determined. The takeover state is then determined based on the takeover mode, threat side, takeover threshold, driver input, and controller input. Once the state of each side is determined, the method can terminate at 714.

[0061] Therefore, methods, systems, and vehicles are provided for steering during driver takeover in lane-based automated assistance functions. It should be understood that the systems, vehicles, and methods may differ from those shown in the accompanying drawings and described herein. For example, Figure 1 Vehicle 10 and Figure 3 System 100 and its components may vary in different embodiments. Similarly, it will be appreciated that the steps of process 700 may differ. Figure 7 The steps shown, and / or the various steps of process 700, may occur simultaneously and / or in different ways. Figure 7 The sequence shown occurs.

[0062] While at least one exemplary embodiment has been described in the foregoing detailed description, it should be understood that numerous variations exist. It should also be understood that the one or more exemplary embodiments are merely examples and are not intended to limit the scope, applicability, or configuration of this disclosure in any way. Rather, the foregoing detailed description will provide those skilled in the art with a convenient roadmap for implementing one or more exemplary embodiments. It should be understood that various changes can be made to the function and arrangement of the elements without departing from the scope of this disclosure as set forth in the appended claims and their legal equivalents.

Claims

1. A method of controlling steering of an autonomous vehicle, comprising: operating, by a processor, the autonomous vehicle in a path-based autonomous driving assist mode; receiving, by the processor, driver input data including a driver steering torque direction and a steering switch direction; and threat data; classifying, by the processor, an operating mode according to a type of the path-based autonomous driving assist mode and based on a detected threat indicated by the threat data; each operating mode defined by the steering switch direction, a threat side, and the driver torque direction; the threat detection indicating whether a threat is detected on a left side of the vehicle or a right side of the vehicle; determining, by the processor, a takeover threshold for a first side of the autonomous vehicle for taking over the path-based autonomous driving assist mode based on the classified operating mode; determining, by the processor, a driver takeover state based on the takeover threshold; and generating, by the processor, a control signal to control steering of the autonomous vehicle based on the driver takeover state and the driver steering torque direction. the path-based autonomous driving assist mode including at least one of a lane keep assist mode, a side collision avoidance mode, and a manual lane centering mode.

2. The method of claim 1, wherein, 3. The method of claim 1, further comprising, in response to detecting a safety barrier exists on a side of the autonomous vehicle, determining a safety barrier takeover threshold, and wherein the takeover threshold is further determined based on the safety barrier takeover threshold. determining the safety barrier takeover threshold is based on a classification of the safety barrier and a barrier dynamic between the autonomous vehicle and the safety barrier.

4. The method of claim 3, wherein, the barrier dynamic including a time to collision and a relative velocity between the autonomous vehicle and the safety barrier.

5. The method of claim 4, wherein, the classification of the safety barrier is based on a type of the safety barrier and a severity of barrier intrusion.

6. The method of claim 4, wherein, the takeover threshold is determined based on a steady state steering torque associated with a lane curvature, a vehicle parameter, and an external disturbance.

7. The method of claim 4, wherein, the external disturbance including at least one of a road angle, a road friction, and a crosswind.

8. The method of claim 7, wherein, the determining the driver takeover state is further based on a magnitude and a direction of a controller torque, a magnitude and a direction of the driver torque, and the steering switch direction.

9. The method of claim 1, wherein, 10. A system for controlling steering of an autonomous vehicle, comprising: a non-transitory computer readable medium comprising computer instructions configured to perform a process; and a processor configured to perform the process, the process comprising: operating, by the processor, the autonomous vehicle in a path-based autonomous driving assist mode; receiving, by the processor, driver input data including a driver steering torque direction and a steering switch direction; and threat data; classifying, by the processor, an operating mode according to a type of the path-based autonomous driving assist mode and based on a detected threat indicated by the threat data; each operating mode defined by the steering switch direction, a threat side, and the driver torque direction; the threat detection indicating whether a threat is detected on a left side of the vehicle or a right side of the vehicle; determining, by the processor, a takeover threshold for a first side of the autonomous vehicle for taking over the path-based autonomous driving assist mode based on the classified operating mode, determining, by the processor, a driver takeover state based on the takeover threshold; and generating, by the processor, a control signal to control steering of the autonomous vehicle based on the driver takeover state and the driver steering torque direction. ​

Images