Vehicle and method for controlling a vehicle

Abstract

The present invention relates to a vehicle and a method for controlling a vehicle. An autonomous vehicle control device can: identify first information related to an attention state of a driver with respect to an autonomous vehicle; identify second information related to a surrounding road environment of the autonomous vehicle; during autonomous driving control of the autonomous vehicle, determine a reference value for setting a warning output condition based on the first information and the second information; and control a warning output of the autonomous vehicle based on the determined reference value.

Description

[0001] Cross-reference to related applications This application claims priority and benefit to Korean Patent Application No. 10-2025-0055426, filed on April 28, 2025, with the Korean Intellectual Property Office, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This invention relates to autonomous vehicles and methods for controlling autonomous vehicles. Background Technology

[0003] While some implementations of driver attention warning systems can provide warning messages when a driver's level of attention declines, they may capture and analyze driver conditions in less detail, and they may always provide the same warning based on some criterion.

[0004] Outputting uniform warning messages without considering driver fatigue and distraction may reduce the effectiveness of warning messages, because drivers may adapt to and become accustomed to those warnings.

[0005] The matters described in this background section are only intended to enhance the understanding of the background art of the present invention and should not be regarded as an admission that they correspond to prior art known to those skilled in the art. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to address the above-mentioned problems. The purpose of the present invention is to analyze the driver's attention state and road environment in real time, and to calculate reference values ​​for setting warning output conditions based on the analysis, thereby providing the driver with targeted warnings.

[0007] The problems to be solved by the present invention are not limited to those described above, and those skilled in the art will understand more clearly from the following description other problems not mentioned.

[0008] According to one or more exemplary embodiments of the present invention, an autonomous vehicle control device may include a processor and a memory. The memory may store at least one instruction, which, when executed by the processor, is configured to cause the autonomous vehicle control device to: identify first information relating to the driver's attention state regarding the autonomous vehicle; identify second information relating to the surrounding road environment of the autonomous vehicle; determine, based on the first and second information, a reference value for setting warning output conditions during autonomous driving control of the autonomous vehicle; and control the warning output of the autonomous vehicle based on the determined reference value.

[0009] The first information may include at least one of the following: the driver's line of sight, the driver's blink, the driver's head position change, or the driver's reaction time to a warning signal inside the vehicle.

[0010] The first information may include the result of learning based on the driver's historical attention state data. At least one instruction, when executed by the processor, may be configured to cause the autonomous vehicle control unit to determine a reference value by comparing the learning result with the driver's attention state collected in real time.

[0011] At least one instruction, when executed by a processor, can be configured to cause the autonomous vehicle control unit to determine a reference value by: identifying third information related to the driver's biometric information; and further determining the reference value based on the third information.

[0012] At least one instruction, when executed by the processor, can be configured to cause the autonomous vehicle control device to determine a reference value in such a way as to determine the reference value based on the driver's driving habits or changes in the surrounding road environment, and based on at least some information selected from first information and second information.

[0013] At least one instruction, when executed by the processor, can be configured to further enable the autonomous vehicle control unit to adjust the reference value in real time.

[0014] At least one instruction, when executed by the processor, can be configured to cause the autonomous vehicle control unit to control the warning output of the autonomous vehicle in the following manner: outputting a first warning including at least one of a visual warning, an auditory warning, or a tactile warning; receiving the driver's reaction to the first warning; and, based on the driver's reaction, outputting a second warning of a different type or a combination of different types from the first warning.

[0015] The surrounding road environment may include at least one of the following: the type of road on which the autonomous vehicle is traveling; traffic around the autonomous vehicle; or weather conditions in the area where the autonomous vehicle is traveling.

[0016] At least one instruction, when executed by the processor, is configured to cause the autonomous vehicle control device to control the warning output of the autonomous vehicle in such a way as to adjust at least one of the type, period, mode, or intensity of the warning output of the autonomous vehicle based on a reference value.

[0017] At least one instruction, when executed by the processor, can be configured to cause the autonomous vehicle control unit to control the warning output of the autonomous vehicle in such a way as to output information related to the control state of the warning output via the input / output interface of the autonomous vehicle.

[0018] According to one or more exemplary embodiments of the present invention, a method performed by means of an autonomous vehicle may include: identifying first information relating to the driver's attention state regarding the autonomous vehicle; identifying second information relating to the surrounding road environment of the autonomous vehicle; determining, based on the first and second information, a reference value for setting warning output conditions during autonomous driving control of the autonomous vehicle; and controlling the warning output of the autonomous vehicle based on the determined reference value.

[0019] The first information may include at least one of the following: the driver's line of sight, the driver's blink, the driver's head position change, or the driver's reaction time to a warning signal inside the vehicle.

[0020] The first piece of information may include the results of learning based on the driver's historical attention state data. Determining the reference value may include: determining the reference value by comparing the learning results with the driver's attention state collected in real time.

[0021] Determining reference values ​​may include: identifying third information related to the driver's biometric information; and determining reference values ​​based on the third information.

[0022] Determining reference values ​​may include: determining reference values ​​based on changes in the driver's driving habits or the surrounding road environment, or based on at least some information selected from first information and second information.

[0023] The warning output for controlling an autonomous vehicle may include: outputting a first warning that includes at least one of a visual warning, an auditory warning, or a tactile warning; receiving the driver's response to the first warning; and outputting a second warning of a different type or a combination of different types from the first warning based on the driver's response.

[0024] The surrounding road environment may include at least one of the following: the type of road on which the autonomous vehicle is traveling; traffic around the autonomous vehicle; or weather conditions in the area where the autonomous vehicle is traveling.

[0025] Controlling the warning output of an autonomous vehicle may include adjusting at least one of the following: the type, period, mode, or intensity of the warning output of the autonomous vehicle based on a reference value.

[0026] Controlling the warning output of an autonomous vehicle may include: outputting information related to the control status of the warning output via the autonomous vehicle's input / output interface.

[0027] According to one or more exemplary embodiments of the present invention, an autonomous vehicle may include: a sensor configured to detect the driver's attention state; a processor; and a memory. The memory may store at least one instruction, configured, when executed by the processor, to cause the autonomous vehicle to: identify a first attention state of the driver via the sensor at a first time; output a first warning signal via an input / output interface of the autonomous vehicle based on the first attention state during autonomous driving control of the autonomous vehicle; determine the driver's reaction time to the first warning signal; identify a second attention state of the driver via the sensor at a second time later than the first time; and output a second warning signal via the input / output interface of the autonomous vehicle based on the second attention state and based on a reaction time greater than a threshold amount of time during autonomous driving control of the autonomous vehicle. The first warning signal may have a first warning signal type, and the second warning signal may have a second warning signal type different from the first warning signal type. Attached Figure Description

[0028] The above and other objects, features and advantages of the present invention will become more apparent to those skilled in the art from a detailed description of one or more exemplary embodiments of the invention with reference to the accompanying drawings.

[0029] Figure 1 This is a schematic diagram of an example component of an autonomous vehicle.

[0030] Figure 2 This is a flowchart of an example method to attract the driver's attention.

[0031] Figure 3 This is a flowchart of an example method for learning a driver's attention state and deriving a score.

[0032] Figure 4 This is a flowchart of an example method for outputting warnings based on risk scores and adjusting the warnings according to the driver's reaction. Detailed Implementation

[0033] In the following, one or more exemplary embodiments of the invention will be described in detail with reference to the accompanying drawings.

[0034] However, the technical concept of the present invention is not limited to the exemplary embodiments described, but can be implemented in various different forms, and within the scope of the technical concept of the present invention, one or more constituent elements can be selectively combined and substituted among different exemplary embodiments.

[0035] Furthermore, unless otherwise explicitly defined and described, the terms used in the exemplary embodiments of the invention (e.g., including technical and scientific terms) may be interpreted as having meanings that would be generally understood by one of ordinary skill in the art to which this invention pertains, and common terms such as predefined terms may be interpreted in light of the contextual meaning of prior art.

[0036] Furthermore, the terminology used in the exemplary embodiments of the present invention is for describing the exemplary embodiments and is not intended to limit the present invention.

[0037] In this specification, unless otherwise specifically stated in the phrase, the singular form may include the plural form, and when described as “at least one (or one or more) of A and / or B and / or C,” this may include one or more of all possible combinations of A, B, and C. For the purposes of this application and claims, the exemplary phrases “at least one of A; B or C” or “at least one of A, B, or C” are used, and the phrases mean “at least one A, or at least one B, or at least one C, or any combination of at least one A, at least one B, and at least one C.” Furthermore, exemplary phrases as used herein, such as “A, B, or C,” “at least one of A, B, and C,” “at least one of A, B, or C,” etc., may represent each enumerated item or all possible combinations of enumerated items. For example, “at least one of A or B” may mean (1) at least one A; (2) at least one B; or (3) at least one A and at least one B.

[0038] In addition, when describing the constituent elements of exemplary embodiments of the present invention, terms such as first, second, A, B, (a), (b) may be used.

[0039] These terms are used only to distinguish constituent elements from other constituent elements, and the nature, order, or sequence of constituent elements are not limited by the terms.

[0040] Furthermore, when a constituent element is described as being "connected", "joined", or "bonded" to another constituent element, it may include not only cases where the constituent element is directly connected, joined, or bonded to other constituent elements, but also cases where the constituent element is "connected", "joined", or "bonded" to another constituent element through another constituent element between the constituent element and other constituent elements.

[0041] Furthermore, when described as being formed or arranged "above (top) or below (under)" of each constituent element, "above (top) or below (under)" includes not only the case where two constituent elements are in direct contact with each other, but also the case where one or more other constituent elements are formed or arranged between two constituent elements. Additionally, when expressed as "above (top) or below (under)", it can include not only the meaning of an upward direction based on a constituent element, but also the meaning of a downward direction based on a constituent element.

[0042] In the various flowcharts of this document, at least some steps may be omitted or their order may be changed, and at least some of the various example embodiments of this document may be executed at a specific point in time for each step of the flowchart. The operations of the various flowcharts in this document may be performed by at least one of the control device 100, the processor 130, and the autonomous vehicle 10. Additionally, repeated content in the accompanying drawings of this document may be omitted. In this document, "control device 100" may also be referred to as "autonomous vehicle control device 100".

[0043] In this document, "driver control assistance system" refers to the hardware and software that assists the driver in continuously controlling the longitudinal and lateral movements of the vehicle. This driver control assistance system may be referred to as an "automatic driving system" or simply "the system" in this document.

[0044] In the document, "features" can refer to specific system functions that provide assistance to drivers in defined traffic scenarios, situations, and system boundaries.

[0045] In this document, "dynamic control" can refer to the operational and tactical functions required to perform actions on a moving vehicle in real time. This can include controlling the vehicle's lateral and longitudinal movement, monitoring the road environment, responding to events in the road traffic environment, planning maneuvers, and signal transmission.

[0046] In this document, “system boundary” may refer to the range of conditions that affect the functionality of a system or system designed to assist a driver and the system’s ability to operate as intended, or within such range of conditions, verifiable or measurable limitations or conditions set by the manufacturer.

[0047] In this document, "risk score" is a value set to determine the warning output condition, and can also be referred to as "reference value".

[0048] According to the Society of Automotive Engineers (SAE), the automation levels of autonomous vehicles can be classified as follows: At Level 0, the SAE classification corresponds to "No Automation," where the automated driving system temporarily intervenes in emergency situations (e.g., automatic emergency braking) and / or only provides warnings (e.g., blind spot warning, lane departure warning, etc.), and expects the driver to operate the vehicle. At Level 1, the SAE classification corresponds to "Driver Assistance," where the system performs some driving functions (e.g., steering, acceleration, braking, lane centering, adaptive cruise control, etc.) when the driver operates the vehicle in normal operating conditions, and expects the driver to determine the system's operating status and / or timing, perform other driving functions, and respond to (e.g., resolve) emergency situations. At Level 2, the SAE classification corresponds to "Partial Automation," where the system performs steering, acceleration, and / or braking under driver supervision, and expects the driver to determine the system's operating status and / or timing, perform other driving functions, and respond to (e.g., resolve) emergency situations. At Level 3 of Automated Driving, the SAE classification standard can correspond to "Conditional Automation," where the system drives the vehicle under limited conditions (e.g., performing driving functions such as steering, acceleration, and / or braking), but transfers driving control to the driver when the required conditions are not met, and expects the driver to determine the system's operating state and / or timing and take over control in emergency situations without otherwise operating the vehicle (e.g., steering, acceleration, and / or braking). At Level 4 of Automated Driving, the SAE classification standard can correspond to "High Automation," where the system performs all driving functions, and expects the driver to control the vehicle only in emergency situations. At Level 5 of Automated Driving, the SAE classification standard can correspond to "Full Automation," where the system performs full driving functions without any driver assistance, including in emergency situations, and expects the driver to perform no driving functions other than determining the system's operating state. Although the present invention can apply the SAE classification standard to automated driving classification, other classification methods and / or algorithms can be used in one or more configurations described herein. One or more features associated with automated driving control can be activated based on the configured automated driving control settings (e.g., based on at least one of the following: automated driving classification, selection of the automated driving level for the vehicle, etc.).

[0049] Based on one or more features described herein (e.g., identifying information related to the driver's attention state and the surrounding road environment), vehicle operation can be controlled. Vehicle control can include various operational controls related to the vehicle (e.g., automatic driving control, sensor control, braking control, braking time control, acceleration control, rate of change of acceleration control, warning timing control, forward collision warning timing control, etc.).

[0050] One or more auxiliary devices (e.g., engine brakes, exhaust brakes, hydraulic reducers, electric reducers, regenerative brakes, etc.) may also be controlled, for example, based on one or more features described herein (e.g., identifying information related to the driver's attention state and the surrounding road environment). One or more communication devices (e.g., modems, network adapters, radio transceivers, antennas, etc., capable of communicating via one or more wired or wireless communication protocols (such as Ethernet, Wi-Fi, near-field communication (NFC), Bluetooth, Long-Term Evolution (LTE), 5G New Radio (NR), vehicle-to-everything (V2X), etc.)) may also be controlled, for example, based on one or more features described herein (e.g., identifying information related to the driver's attention state and the surrounding road environment).

[0051] Minimum risk maneuver (MRM) operations can also be controlled, for example, based on one or more features described herein (e.g., identifying information related to the driver's attention state and the surrounding road environment). Minimum risk maneuver operations (e.g., minimum risk strategy, lowest risk strategy) can be policy operations of the vehicle to minimize (e.g., reduce) the risk of collisions with surrounding vehicles to achieve a reduced (e.g., lowest) risk state. Minimum risk strategies can be operations that can be activated during autonomous driving when the driver is unable to respond to intervention requests. During a minimum risk strategy, one or more processors in the vehicle can control the vehicle's driving operations for a set time period.

[0052] Biased driving can also be controlled, for example, based on one or more features described herein (e.g., identifying information related to the driver's attention state and the surrounding road environment). A driving control device can perform biased driving control. To perform biased driving, the driving control device can control the vehicle to stay within the lane by maintaining the lateral distance between the vehicle's center position and the lane center. For example, the driving control device can control the vehicle to stay within the lane rather than in the center of the lane.

[0053] Driving control equipment can identify a target lateral distance for bias driving control. For example, the target lateral distance may include an intentionally adjusted lateral distance that the vehicle aims to maintain with respect to a reference point (e.g., the center of the lane or another vehicle) during maneuvers such as lane changes. This adjustment can be made to improve the vehicle's stability, safety, and / or performance under changing driving conditions. For instance, during lane changes, taking into account factors such as vehicle speed, road conditions, and / or the presence of obstacles, the driving control system may bias the lateral distance to maintain a safer clearance from adjacent vehicles.

[0054] Autonomous driving levels and / or autonomous driving activation / deactivation can also be controlled, for example, based on one or more features described herein (e.g., identifying information related to the driver's attention state and the surrounding road environment). Driving control devices can perform autonomous driving level control (e.g., changing the autonomous driving level, changing the required user attention, etc.) or deactivate autonomous driving operation. For example, changing the required user attention may require the driver to place his / her hands on the steering wheel more frequently (e.g., at least once within a threshold time period (e.g., 5 seconds, 30 seconds, 1 minute, etc.)). Changing the required user attention may require the driver to look forward more frequently (e.g., at least once within a threshold time period (e.g., 5 seconds, 30 seconds, 1 minute, etc.)). Changing the autonomous driving level may prevent the display of one or more video contents from being shown on the vehicle's displays.

[0055] One or more sensors (e.g., IMU sensors, cameras, LIDAR, RADAR, blind spot monitoring sensors, lane departure warning sensors, parking sensors, light sensors, rain sensors, traction control sensors, anti-lock braking system sensors, tire pressure monitoring sensors, seat belt sensors, airbag sensors, fuel sensors, emission sensors, throttle position sensors, inverters, converters, motor controllers, power distribution units, high-voltage wiring and connectors, auxiliary power modules, charging interfaces, etc.) may also be used for control, for example, based on one or more features described herein (e.g., identifying information related to the driver's attention state and the surrounding road environment).

[0056] Operational control for autonomous driving of a vehicle may include various driving controls of the vehicle performed by vehicle control units (e.g., acceleration, deceleration, steering control, gear shifting control, braking system control, traction control, stability control, cruise control, lane keeping assist control, collision avoidance system control, emergency braking assist control, traffic sign recognition control, adaptive headlight control, driver warning control, operational design domain (ODD), activation and / or deactivation of autonomous driving modes, etc.). One or more auxiliary devices (e.g., engine brakes, exhaust brakes, hydraulic reducers, electric reducers, regenerative brakes, etc.) may also be controlled, for example, based on one or more features described herein (e.g., identifying information related to the driver's attention state and the surrounding road environment). One or more communication devices (e.g., modems, network adapters, radio transceivers, antennas, etc., capable of communicating via one or more wired or wireless communication protocols such as Ethernet, Wi-Fi, near-field communication (NFC), Bluetooth, Long-Term Evolution (LTE), 5G New Radio (NR), vehicle-to-everything (V2X), etc.)) may also be controlled, for example, based on one or more features described herein (e.g., assessing the driver's engagement status).

[0057] A vehicle actively controlled by an autonomous driving system can be referred to as an ego vehicle, the vehicle itself, or an autonomous vehicle. An ego vehicle can also be referred to as an autonomous car, an autonomous car (AC), a driverless car, a robotaxi, a robotic car, or a robo-car. An ego vehicle can be a vehicle equipped with an autonomous driving system. Alternatively, the autonomous driving system can control the ego vehicle, for example, from an external and / or remote device such as a server. The ego vehicle can be remotely controlled (e.g., driven, manipulated, etc.) partially or fully by a remote human driver. A vehicle in front of the ego vehicle (e.g., in the same lane as the ego vehicle) can be referred to as a vehicle in front (e.g., directly in front), a leading vehicle, a guiding vehicle, or a vehicle ahead. A vehicle following the ego vehicle (e.g., in the same lane as the ego vehicle) can be referred to as a vehicle behind, a trailing vehicle, a following vehicle, or a successor vehicle. Neighboring vehicles can refer to any vehicle located in any direction (e.g., in front, behind, to the left, to the right, diagonally, etc.) of the vehicle, provided that there are no other vehicles (e.g., intermediate vehicles) between them (e.g., regardless of their distance from the vehicle). Alternatively, in some contexts, only those vehicles located within a threshold distance (e.g., line of sight and / or the detection limits of one or more sensors of the vehicle) can be referred to as neighboring vehicles. Target vehicles can be any vehicle near the vehicle (e.g., within a threshold distance). Target vehicles can be any vehicle that the autonomous driving system actively or passively monitors, identifies, tracks, and / or analyzes, once or multiple times, and occasionally or continuously. The threshold distance can be, for example, line of sight and / or the detection limits of one or more sensors of the vehicle, but the threshold distance can be a value smaller than the line of sight and / or the detection limits of one or more sensors of the vehicle (e.g., an adjustable value). The target vehicle can be, for example, a vehicle in front, a vehicle behind, a vehicle in a lane different from the vehicle's own lane (e.g., a vehicle on the left, a vehicle on the right, a vehicle diagonally opposite, etc.), and / or a nearby vehicle (e.g., regardless of the distance from the vehicle and / or regardless of whether there is a vehicle in between the target vehicle and the vehicle). The target vehicle can also be referred to as a surrounding vehicle, a nearby vehicle, an external vehicle, another vehicle (other vehicle), etc.

[0058] The steps in the flowcharts mentioned in this document can be written to be executed by the processor 130 of the autonomous vehicle 10, but are not limited thereto, and each step can be executed by the control device 100 or the autonomous vehicle 10 itself in an example implementation.

[0059] In the following, one or more exemplary embodiments will be described in detail with reference to the accompanying drawings, but regardless of the reference numerals, the same or corresponding constituent elements will be given the same reference numerals, and redundant descriptions will be omitted.

[0060] Figure 1 This is a schematic diagram of an example component of an autonomous vehicle 10.

[0061] The autonomous vehicle 10 may include a control unit 100, a communication unit 110, a storage unit 120, a processor 130, an input / output interface 140, a sensor unit 150, and a drive unit 160. Figure 1 Each of these components can be implemented inside the vehicle.

[0062] The autonomous driving system can dynamically control the autonomous vehicle 10 under various driving conditions. For example, the autonomous driving system can provide both driving stability and convenience through longitudinal control (e.g., acceleration and deceleration) and lateral control (e.g., lane keeping and changing) of the autonomous vehicle 10. The autonomous driving system can monitor the driving environment through sensors and control devices, and process the data in real time to adjust the vehicle's position, speed, direction, etc.

[0063] The control unit 100 can be integrated with the vehicle's internal components or implemented as a separate device from other components within the autonomous vehicle 10, and communicate with the vehicle's internal components via various connectivity devices (e.g., CAN bus, wireless network, wired connection, etc.). The control unit 100 includes a communication unit 110, a storage unit 120, and a processor 130 to manage the vehicle's longitudinal and lateral control, and may additionally include other components such as an input / output interface 140, a sensor unit 150, and a drive unit 160 to perform complex control functions based on driving conditions.

[0064] The control unit 100 can store data collected from the sensor unit 150 during driving in the storage unit 120 and process the data in real time to control the vehicle's safety and convenience functions. For example, the control unit can perform overall control and management of the autonomous driving system based on the data detected from the sensor unit 150, such as providing notifications when driver intervention is required.

[0065] The control device 100 can display the vehicle control status or receive driver input to control driving functions through a user interface linked to a human-machine interface (HMI) based on various driver settings and driving conditions.

[0066] The control device 100 can analyze the driver's attention state and the road environment around the vehicle in real time. The control device 100 can collect data such as the driver's gaze direction, blinking patterns, head direction changes, and whether the mobile phone is being operated, and can assess the risk level by combining it with the road environment (e.g., weather conditions, road type, traffic flow).

[0067] The communication unit 110 can communicate with other control devices inside the vehicle to share data between systems, or it can send and receive various information through a connection to the outside of the vehicle. The communication unit 110 uses various in-vehicle communication methods such as CAN communication and Ethernet to send control signals and data between internal components, and can link driving information and external data in real time through communication with user terminals, other vehicles (V2V), infrastructure (V2I), or external servers.

[0068] The communication unit 110 can perform short-range communication, Global Navigation Satellite System (GNSS) module (e.g., GPS module), vehicle-to-everything (V2X) communication, optical communication, broadcast transmission and reception, and Intelligent Transport Systems (ITS) communication functions. For example, the communication unit 110 can utilize various wireless communication technologies such as Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, Near-Field Communication (NFC), Wi-Fi, Wi-Fi Direct, and Wireless USB to support stable data transmission over short distances. Furthermore, long-range communication can be achieved through mobile communication modules and wireless internet modules based on mobile communication networks such as LTE and 5G to receive real-time data or interact with the cloud, thereby improving the performance of the autonomous driving system.

[0069] The communication unit 110 can receive external data (e.g., weather information, traffic flow data, etc.) from an external server.

[0070] Storage unit 120 may include various types of memory capable of storing data and may be integrated into control device 100 or processor 130, or configured as a separate module. Storage unit 120 may include non-volatile memory (e.g., hard disk drive, flash memory, etc.) and volatile memory, and may be combined to implement memory systems with various capacities and performance characteristics.

[0071] Storage unit 120 may include a memory capable of storing and managing various data related to the autonomous driving system.

[0072] Storage unit 120 can store driving data representing the driver's driving habits and build a targeted warning database for individual drivers based on this data.

[0073] The processor 130 can communicate with the communication unit 110, storage unit 120, input / output interface 140, sensor unit 150, drive unit 160, and various internal components of the autonomous vehicle 10 via electrical or operative connections, and controls the operation of each component and performs data processing. The processor 130 is a central processing unit for executing instructions and calculating data, and can collect, process, and analyze data in real time according to the vehicle's driving environment to perform vehicle control.

[0074] The processor 130 can be implemented in hardware, software, or a combination thereof, and can execute vehicle control logic in the form of, for example, a microcontroller, a field-programmable gate array (FPGA), or an application-specific integrated circuit (ASIC). Additionally, the processor 130 can include a multiprocessor configuration for controlling complex autonomous driving and driver assistance systems. This processor configuration can support the overall control and stability performance of the vehicle by performing autonomous driving and assistance systems, sensor data processing, communication data management, and driving-related decision-making functions.

[0075] The processor 130 can calculate a risk score by comprehensively analyzing the driver's attention state and the road environment, and dynamically adjust the warning system accordingly.

[0076] The input / output interface 140 receives vehicle control-related input from the user and plays a role in communicating the vehicle's control status and system operation information to the user.

[0077] The input / output interface 140 can perform functions such as receiving various inputs from the user and communicating the vehicle control status to the user. For example, the input / output interface 140 may include at least one of the following: input via physical buttons located inside the autonomous vehicle 10, input via soft buttons displayed on a display of the autonomous vehicle 10, user voice input, and user gesture input.

[0078] Input devices may include physical buttons, soft keys on a touch display, voice recognition, gesture recognition, etc., which allow users to input commands such as requests to activate autonomous driving systems, change functions, or set driver assistance settings.

[0079] Additionally, the input device can receive user input via an input device mounted on the steering wheel of the autonomous vehicle 10. For example, the driver can input commands to activate or deactivate the autonomous driving system even while driving via buttons mounted on the steering wheel. This steering wheel-based input allows users to quickly control autonomous driving functions by providing an intuitive interface.

[0080] Output devices include displays, audio modules (e.g., speakers), haptic modules, etc., and can provide users with information such as the status of the autonomous driving system, control change request notifications, and whether functions are activated in a visual, auditory, and tactile manner.

[0081] Additionally, the status of the autonomous driving system can be visually checked via a head-up display (HUD), instrument cluster, audio video navigation (AVN), and displays built into the rearview or side mirrors. Furthermore, the status of the autonomous driving system can be checked via displays on the control consoles installed in each row of the autonomous vehicle 10, user terminal applications, etc.

[0082] The input / output interface 140 can perform the function of receiving input from the driver and outputting vehicle control status and system operation information to the user. The input / output interface 140 can utilize visual, auditory, and tactile cues to provide various types of warnings. The input / output interface (also called the input and output interface) 140 can output information about the control status of the warning output (e.g., whether the warning output is currently active, whether the output intensity or cycle has been adjusted, whether the output method has been changed, etc.).

[0083] Sensor unit 150 may include multiple sensors that support stable operation of the autonomous driving system by detecting various driving and environmental information in real time. Sensor unit 150 may use long-range detection sensors such as radar and lidar to measure distance and speed to surrounding objects, and may include ultrasonic sensors to detect objects near the autonomous vehicle 10.

[0084] Additionally, the sensor unit 150 may include a position sensor, such as a GPS sensor, to collect position information of the autonomous vehicle 10, and may include an optical sensor to provide ambient illumination information, enabling the system to respond to changes in light. Furthermore, the sensor unit 150 may include accelerator and deceleration pedal sensors, a steering wheel detection sensor, seat sensors, etc., to monitor the driving control status of the autonomous vehicle 10 and user operations.

[0085] Sensor unit 150 may include a camera. The camera may be classified as an external camera and an internal camera. The external camera identifies the road and the surrounding environment, while the internal camera can gain a comprehensive understanding of the situation inside and outside the vehicle by detecting the driver's state (e.g., eye tracking, drowsiness detection) or the situation inside the vehicle.

[0086] The sensor unit 150 may include a heart rate sensor, a pressure sensor, an infrared sensor, etc., to collect the driver's biometric information or various environmental data.

[0087] The sensor unit 150 may include sensors capable of detecting the driver's biometric information. For example, the sensor unit 150 may use a heart rate sensor or an infrared camera to determine the driver's fatigue state.

[0088] The drive unit 160 provides the driving force required for the autonomous vehicle 10 to move, and may include various components that control the operation of the vehicle according to instructions output from the control unit 100. The drive unit 160 may consist of devices such as an engine, an electric motor, a transmission, and a wheel drive system that generate and transmit power to the vehicle, as well as controllers that control these devices, and through these components, the autonomous vehicle 10 can perform acceleration, deceleration, and direction changes.

[0089] The drive unit 160 can be controlled to maintain driving safety by performing longitudinal control (e.g., acceleration and deceleration) and lateral control (e.g., lane keeping and changing). For example, the drive unit 160 receives instructions from the control unit 100 to adjust the output of the motor or adjust the speed and direction of the wheels so that the vehicle can travel along the driving path.

[0090] Additionally, the drive unit 160 may include a braking system to reduce or stop the vehicle speed during operation. The drive unit 160 can control the autonomous vehicle 10 based on the control of an electric motor in the case of an electric vehicle, and based on engine output in the case of an internal combustion engine vehicle.

[0091] When the driver's attention drops sharply, the drive unit 160 can perform functions such as adjusting the vehicle's speed or automatically stopping under certain conditions.

[0092] Figure 2 This is a flowchart of an example method to attract the driver's attention.

[0093] The processor 130 can identify first information related to the driver's attention state (S210).

[0094] Specifically, the processor 130 can identify first information including at least one of the driver’s gaze direction, blinking, head direction change, or reaction speed (e.g., reaction time) to in-vehicle warning signals.

[0095] For example, processor 130 can analyze the driver's gaze vector using sensor unit 150, such as an internal camera, to determine if the driver's attention is distracted when the driver does not look forward for a specific period of time. Additionally, an increase in blinking frequency or an increase in the duration of eye closure can be assessed as drowsiness. Furthermore, processor 130 can monitor changes in head orientation (e.g., orientation) to identify a state of distraction when the driver is continuously looking away from what is directly in front of them.

[0096] The processor 130 can detect driver operation of a mobile phone based on whether the screen of a user terminal, such as a smartphone, is active. When the vehicle and the smartphone are connected via Bluetooth or similar means, the processor 130 can analyze whether a specific application is being used to assess the likelihood of mobile phone use while driving. Alternatively, the processor 130 can determine whether the mobile phone is being operated by utilizing onboard motion sensors or accelerometers to detect patterns of repeated hand movements by the driver.

[0097] The processor 130 can analyze the driver's reaction speed (e.g., reaction time) to in-vehicle warning signals (e.g., warning sounds, HUD notifications, haptic feedback, etc.). For example, if the driver does not apply the brakes or operate the lever within a predetermined time after a warning is issued, the processor 130 can determine that the reaction speed is slow. When the reaction speed is continuously delayed, the processor 130 can assess that the driver is fatigued or has impaired cognitive ability.

[0098] The processor 130 can identify second information related to the surrounding road environment (S220).

[0099] Specifically, the processor 130 can receive data from sensor units 150 located outside the vehicle to analyze information such as road type, movement of surrounding vehicles, presence or absence of pedestrians, and weather conditions. This information can correspond to second information. Furthermore, the second information can be received from an external server.

[0100] Specifically, the second information may include at least one of the following: road type information, traffic information around the vehicle, and weather information of the area where the vehicle is traveling.

[0101] For example, when the vehicle is traveling on a highway, the processor 130 can analyze the speeds of surrounding vehicles to assess the relative speed difference of the autonomous vehicle 10. Additionally, since the likelihood of pedestrians or personal mobility devices (PMs) is higher on ordinary roads, the processor 130 can notify the driver when a pedestrian or PM is detected.

[0102] The processor 130 can collect weather information via an embedded weather sensor or an external network of the vehicle. It can also collect weather information on visibility-limiting factors such as rain, snow, and fog.

[0103] On the other hand, the processor 130 can collect and analyze the driver's biometric information to assess attention status.

[0104] Specifically, the processor 130 can identify third information including biometric data such as the driver's heart rate (HR), heart rate variability (HRV), skin electrical response (GSR), and breathing pattern.

[0105] For example, processor 130 can analyze heart rate to detect drowsiness. Typically, heart rate tends to decrease and heart rate variability tends to decrease as fatigue accumulates. Such data can be measured via vehicle radar sensors, wearable devices (e.g., smartwatches, smart bracelets), biometric sensors embedded in steering wheels, etc.

[0106] Additionally, the processor 130 can analyze breathing patterns to assess whether the driver is stressed or drowsy. For example, deep, steady breathing can indicate a stable state, while shallow, irregular breathing can indicate drowsiness or stress. Furthermore, the skin conductance response (GSR) can be used as an indicator of emotional arousal or level of concentration.

[0107] The processor 130 can be associated with various sensors in the vehicle to sense breathing patterns. For example, the processor 130 can use infrared cameras, radar-based biometric sensors, etc., to detect the driver's chest or abdominal movements to measure respiratory rate. In addition, the processor 130 can measure the driver's heart rate (HR) and heart rate variability (HRV) by using a steering wheel that includes an electrocardiogram (ECG) sensor.

[0108] The processor 130 can calculate a risk score (e.g., a reference value) by comprehensively analyzing the driver's attention state and the road environment (S230).

[0109] Specifically, the processor 130 can comprehensively analyze first information (e.g., the driver's attention state), second information (e.g., road environment, weather information, etc.) and third information (e.g., the driver's biometric information) to assess the risk level.

[0110] The risk level may increase when a driver does not look ahead for an extended period, or when blinking frequency increases. Additionally, complex road conditions, heavy traffic congestion, or poor weather conditions may require further weighting and assessment of the risk level.

[0111] For example, the risk score can be determined using the following equation: Risk Score = (W1 × Driver Attention Level) + (W2 × Road Environment Risk Level) + (W3 × Traffic Condition Risk Level) + (W4 × Biometric Information Risk Level) Here, W1, W2, W3, and W4 are the weights used for each element, and they can be dynamically adjusted in certain situations.

[0112] The processor 130 can select weights W1 to W4 from a pre-stored database DB, or it can calculate values ​​suitable for a specific situation using artificial intelligence (AI) and deep learning-based models. In the database, the states of driver attention, road environment risk level, traffic condition risk level, and biometric information risk level can be mapped to corresponding numerical values ​​and are pre-stored in predetermined numbers. Furthermore, the database can be continuously updated.

[0113] Additionally, the processor 130 can learn the driver's driving history data (e.g., historical attention state data), and when maintaining a stable driving pattern even when a particular driver frequently shifts their gaze, the weight W1 for the driver's attention state can be reduced, while the weight W2 for the road environment risk level or the weight W4 for the biometric information risk level can be relatively increased. On the other hand, in the case of a new driver, all weights can be set to default values, or a standard model can be applied.

[0114] The weight W2 used for road environment risk level can include weather information, and can be analyzed in real time via external sensors of the vehicle (e.g., temperature sensors, humidity sensors, rain detection sensors, etc.) and a network module that receives external weather data. For example, in environments with heavy snowfall or a high probability of road icing, the risk level may automatically increase.

[0115] Additionally, the processor 130 can take into account the vehicle's real-time driving data when calculating the risk score. For example, when driving patterns such as rapid acceleration, rapid braking, or lane departure are detected, the corresponding data can be reflected in the risk score calculation model to perform a more accurate risk assessment.

[0116] The processor 130 can determine a risk score by applying different weights to at least some of the information included in the first or second information based on changes in the driver's driving habits or road conditions. In other words, the processor 130 can determine a reference value by selectively reflecting at least some of the information included in the first or second information based on changes in the driver's driving habits or road conditions.

[0117] For example, when a driver maintains safe driving habits even when frequently shifting their gaze, the processor 130 can relatively reduce the weight W1 of the driver's attention state and adjust the weight W4 of biometric information or the weight W2 of road environment risk level to perform a more accurate assessment. On the other hand, when a driver repeatedly performs rapid acceleration or rapid braking, the driving habits are assessed as dangerous, and the weight W1 used for the driver's attention state or the weight W3 used for the traffic condition risk level (e.g., traffic condition risk) can be increased.

[0118] The processor 130 can change (e.g., adjust) the risk score in real time.

[0119] Specifically, the processor 130 can dynamically adjust the risk score by taking into account real-time changes in the driver's state (e.g., detecting drowsiness, increased stress), sudden changes in the road environment (e.g., sudden traffic congestion, weather changes), and on-board sensor data (e.g., steering wheel operation frequency, detecting sudden braking).

[0120] For example, when a driver shows slight signs of drowsiness, the intensity of the warning can be reduced, but when drowsiness worsens, the risk score can be immediately increased to issue a strong warning. Additionally, while the frequency of warnings can be reduced when traffic flow is smooth, the risk score can be changed (e.g., adjusted) in real time to increase the intensity of the warning in the event of sudden congestion.

[0121] The processor 130 can set weights based on past driving data and driver profiles stored in the database DB, and can apply weights that reflect real-time driving data by utilizing AI and deep learning-based learning algorithms.

[0122] In this way, the processor 130 can dynamically calculate a risk score by taking into account various factors including the driver’s attention state (e.g., first information), road environment (e.g., second information, weather information, etc.), biometric information (e.g., third information) and real-time driving data, and can perform weight setting by a database (DB)-based selection method or an artificial intelligence (AI) and deep learning learning method.

[0123] The processor 130 can control the output of warnings based on the calculated risk score (S240).

[0124] Specifically, when the risk score exceeds a preset threshold, the processor 130 can output one or more visual, auditory, and tactile warnings to the driver. Visual warnings can provide hazard information via a HUD or display. Auditory warnings can notify the driver of the hazardous situation via warning sounds or voice guidance. Tactile warnings can attract the driver's attention via steering wheel vibration or seatbelt tightening function.

[0125] For example, when driver inattention is detected, processor 130 may flash ambient light or display a warning message via HUD or other display. If more serious inattention persists, a loud warning sound may be output or plate vibration may be activated.

[0126] The processor 130 can continuously monitor the driver's reactions and select the most effective warning method. For example, if a particular driver reacts quickly to an auditory warning, the frequency of auditory warnings can be increased in similar situations. Conversely, if a particular driver is more sensitive to tactile warnings, seat vibration warnings can be prioritized.

[0127] Figure 3 This is a flowchart illustrating an example method for learning a driver's attention state and deriving a score. (Compared to...) Figure 2 The content is repetitive. Figure 3 The content can be briefly described or omitted.

[0128] The processor 130 can collect data from the driver monitoring system to assess the driver's attention status in real time (S310).

[0129] The processor 130 can continuously monitor the driver's attention state by utilizing an internal camera, an infrared (IR) camera, a steering wheel sensor, a radar-based biometric sensor, etc., included in the sensor unit 150.

[0130] The processor 130 can distinguish and monitor different parts of the driver's body individually.

[0131] For example, to detect the driver's head and face, the processor 130 can use an internal camera or an IR camera to analyze the direction of gaze, blink frequency, facial tilt, etc. If the driver is not looking ahead or keeps their eyes closed for an extended period, their attention may be distracted or the driver may be identified as drowsy.

[0132] Additionally, the processor 130 can utilize the steering wheel sensor to monitor the driver's hand and arm movements. For example, if the driver has not held the steering wheel for an extended period or has not operated the steering wheel for a specific time, it can be determined that the driver's attention has decreased.

[0133] Additionally, the processor 130 can utilize radar-based biometric sensors to sense the driver's upper body movements. For example, when the driver's upper body is continuously tilted or not facing forward, it can be determined that the driver's fatigue level is increasing or their attention is being diverted.

[0134] Therefore, the processor 130 can analyze the driver's body parts individually to perform a more accurate assessment of attention status.

[0135] The processor 130 can learn the driver's driving habits to build a personalized attention state assessment model (S320).

[0136] Specifically, the processor 130 can collect long-term driving data from the driver to analyze driving habits and attention patterns.

[0137] For example, some drivers may frequently and regularly shift their gaze but still maintain safe driving. On the other hand, some drivers may experience a decrease in driving stability even with brief gaze shifts. Processor 130 can learn these individual driver characteristics to improve the accuracy of attention state assessment.

[0138] The processor 130 can use a database DB or apply a deep learning-based model to learn the driver's driving habits.

[0139] For example, when a driver frequently performs rapid acceleration and braking, the processor 130 can learn this as an unstable driving pattern and reflect it when calculating the risk score. On the other hand, when a driver maintains smooth acceleration and deceleration at a constant speed, the risk assessment model can be adjusted by learning stable driving habits.

[0140] In addition, the processor 130 can learn the driver's corresponding patterns based on the road environment. For example, when the driver is attentive on a highway but has a lot of eye movement on a regular road, it can perform targeted risk assessments based on the road environment.

[0141] The processor 130 can compare the collected driver attention state (e.g., historical attention state data) with the learned driving habit data to derive a score (S330).

[0142] Specifically, the processor 130 can analyze in real time whether the sensed attention state is within the normal range based on the driver's long-term driving habit data.

[0143] Here, real-time attention status can include data such as the driver's gaze direction, blink frequency, head movement, reaction speed, etc., and the learned driving habit data can provide a standard for normal attention status based on past driving patterns.

[0144] The processor 130 can compare real-time (e.g., accumulated) driver attention state data (e.g., historical attention state data) with the learned model to assess whether the driver is maintaining a normal level of attention. For example, when a driver typically has a habit of frequently moving their eyes, assessing the risk level solely by eye movement is not high, and a distracted state can only be identified when the risk level exceeds a certain threshold.

[0145] As described above, the processor 130 can calculate a risk score by comprehensively analyzing first information (e.g., the driver's attention state), second information (e.g., road environment, weather conditions, etc.) and third information (e.g., the driver's biometric information).

[0146] The processor 130 can additionally apply machine learning or deep learning models to the driver's driving habits and real-time data when calculating the risk score.

[0147] For example, processor 130 can assess the driver's attention state in real time based on learned driver driving habit data, select weights from an existing database DB, or dynamically adjust the weights via a machine learning-based model.

[0148] Specifically, the processor 130 can analyze in real time whether the sensed attention state is within the normal range based on the driver's long-term driving habit data.

[0149] The processor 130 can analyze driver attention state data (e.g., in real time) by utilizing machine learning or deep learning-based models, and evaluate whether the real-time data belongs to a normal driving mode through the learned model.

[0150] For example, when drivers typically have a habit of frequently shifting their gaze, the learned model can adjust to reduce the impact of gaze movement, thus avoiding unnecessary risk. On the other hand, when drivers tend to slow their reaction time due to recent fatigue, the learned model can increase the importance of reaction speed to perform more sensitive assessments.

[0151] thus, Figure 3 The driver's attention score results obtained during the process can be compared with Figure 2 The publicly disclosed risk score calculation process enables real-time dynamic risk assessment.

[0152] Figure 4 This is a flowchart of an example method for outputting warnings based on risk scores and adjusting the warnings according to the driver's reaction.

[0153] Processor 130 can be based on the above Figures 2 to 3 The calculated risk score is used to output the first warning.

[0154] Specifically, the processor 130 can output a first warning (S410) in the form of at least one of visual, auditory, and tactile warnings, based on a risk score calculated based on the driver's attention state and the road environment.

[0155] More specifically, the processor 130 can analyze a risk score derived from the driver’s attention state (e.g., first information), road environment (e.g., second information, weather information, etc.) and biometric information (e.g., third information), and adjust at least one of the type, period, pattern and intensity of the warning output corresponding to the risk score.

[0156] The processor 130 can control the warning output in a stepwise manner based on the risk score.

[0157] Specifically, the processor 130 may first provide a visual warning when the risk score is low, and additionally output an auditory and tactile warning when the risk score increases (e.g., if) the risk score increases.

[0158] For example, when the driver's gaze is only diverted for a specific period of time, the processor 130 can output a visual attention message via a display. However, when the driver has not been looking ahead for an extended period or is detected to be drowsy, an auditory warning can be added, and when the risk score increases further, tactile warnings such as seat vibration or steering wheel vibration can be activated.

[0159] Additionally, when the risk score increases sharply (e.g., when a pedestrian suddenly appears in front of the vehicle), a loud warning sound can be output and a high-intensity warning can be provided, such as fastening the seat belt.

[0160] The processor 130 can be configured to increase the frequency and intensity of warning outputs as the risk score increases.

[0161] Specifically, the processor 130 can analyze the calculated risk score in real time, select and output at least one of visual warnings, auditory warnings and tactile warnings according to the corresponding risk level, and gradually adjust the frequency and intensity of the warnings as the risk score increases.

[0162] The processor 130 can confirm the driver's response to the output warning (S420).

[0163] Specifically, the processor 130 can analyze whether the driver has reacted appropriately within a specific time period after the warning is output.

[0164] For example, if the driver immediately applies the brakes or steers to maintain lane position after the warning is issued, the processor 130 can assess that the warning has been effective. On the other hand, a stronger warning can be provided if the driver does not react at all, or if the driver's attention remains distracted after the warning.

[0165] The processor 130 can learn the driver's warning response patterns.

[0166] For example, if a particular driver is sensitive to one type of warning (e.g., auditory warning) (e.g., the driver's reaction time is less than a threshold amount of time) but reacts more slowly to another type of warning (e.g., visual warning) (e.g., the driver's reaction time is greater than a threshold amount of time), then processor 130 can increase the frequency of warning types (e.g., auditory warnings) that the driver has historically been more likely to react to and adjust the intensity of warning types (e.g., visual warnings) that the driver has historically been less likely to react to.

[0167] Furthermore, the processor 130 can be configured to adjust the type, period, mode, or intensity of the warning output if the driver becomes familiar with the same warning pattern and the warning effect decreases. For example, if the driver's reaction to a particular type, period, mode, or intensity of the warning output weakens over time (e.g., the time it takes for the driver to react to the warning output is longer than a threshold amount of time), one or more of the type, period, mode, and / or intensity can be adjusted. For example, different types (e.g., visual instead of auditory, or vice versa), different periods (e.g., longer or shorter alarms, more frequent or less frequent alarms, etc.), different modes (e.g., visual alarm following an auditory alarm, or vice versa), and / or different intensities (e.g., louder or softer alarms, etc.) can be used.

[0168] The processor 130 can output a second warning (S430) that is different from or a combination of different types of the first warning based on the driver's reaction.

[0169] Specifically, the processor 130 can adjust the intensity, type, and frequency of the warning based on whether the driver responds to the first warning. For example, if the driver does not respond to the first visual warning, an auditory warning and a tactile warning can be provided in a second step.

[0170] Additionally, the processor 130 can dynamically change (e.g., adjust) the combination of warning types to adjust the driver's response to be most effective. For example, in a similar hazardous situation, if the driver does not react to a visual warning but immediately reacts to a tactile warning (e.g., seat vibration), the frequency of the tactile warning can be increased and the frequency of the visual warning can be decreased.

[0171] In addition, when driver fatigue is continuously detected, processor 130 can provide targeted warning messages recommending rest instead of repeated warnings.

[0172] Therefore, the processor 130 can learn the driver's reaction in real time and dynamically adjust the warning output to maximize the effectiveness of the warning system.

[0173] An autonomous vehicle control device may include: a memory; and one or more processors connected to the memory, wherein the one or more processors may be configured to: identify first information related to the driver's attention state, identify second information related to the surrounding road environment of the vehicle, determine a reference value for setting warning output conditions based on the first and second information, and control the warning output of the autonomous vehicle based on the determined reference value.

[0174] The first piece of information may include at least one of the driver’s line of sight, blinking, head movement, or reaction speed to warning signals inside the vehicle.

[0175] The first information may include the results of learning based on accumulated driver attention state data, and one or more processors may be configured to compare the learning results with driver attention states collected in real time to calculate reference values.

[0176] One or more processors may be configured to: identify third information related to the driver's biometric information; and further determine reference values ​​based on the third information.

[0177] One or more processors may be configured to determine reference values ​​by selectively reflecting at least some information included in a first or second set of information, based on changes in the driver's driving habits or road conditions.

[0178] One or more processors can be configured to change the reference value in real time.

[0179] One or more processors may be configured to: output a first warning via at least one of a visual warning, an auditory warning, and a tactile warning; confirm the driver's reaction to the output warning; and output a second warning of a different kind or combination from the first warning based on the driver's reaction.

[0180] The second information may include at least one of the following: information about the type of road the vehicle is traveling on, traffic information around the vehicle, or weather information about the area where the vehicle is traveling.

[0181] One or more processors may be configured to adjust at least one of the types, periods, modes, or intensities of warning output based on reference values.

[0182] One or more processors can be configured to output information about the control status of warning outputs via the input / output interface of the autonomous vehicle.

[0183] A method for controlling an autonomous vehicle may include: identifying first information related to the driver’s attention state; identifying second information related to the surrounding road environment of the vehicle; determining reference values ​​for setting warning output conditions based on the first and second information; and controlling the warning output of the autonomous vehicle based on the determined reference values.

[0184] The first information related to the driver’s attention state may include at least one of the driver’s gaze direction, blinking, head direction change, or reaction speed to warning signals inside the vehicle.

[0185] The first information related to the driver's attention state may include the results of learning based on accumulated driver attention state data, and a reference value may be calculated by comparing the learning results with the first information related to the driver's attention state collected in real time.

[0186] A method according to one or more embodiments of the present invention may include: identifying third information related to the driver's biometric information; and determining a reference value based on the third information related to the driver's biometric information.

[0187] Reference values ​​can be determined based on changes in the driver's driving habits or road environment by selectively reflecting at least some information, including first information related to the driver's state of attention or second information related to the surrounding road environment of the vehicle.

[0188] The reference value can be changed in real time.

[0189] The method may further include: outputting a first warning via at least one of a visual warning, an auditory warning, and a tactile warning; confirming the driver's response to the output warning; and outputting a second warning of a different kind or combination from the first warning based on the driver's response.

[0190] The second information relating to the road environment around the vehicle may include at least one of the following: information about the type of road the vehicle is traveling on, traffic information around the vehicle, or weather information in the area where the vehicle is traveling.

[0191] At least one of the warning output type, period, mode, or intensity can be adjusted based on a reference value.

[0192] Information about the control status of warning outputs can be output via the input / output interface of the autonomous vehicle.

[0193] By comprehensively analyzing the driver's attention state and road environment to control warning output, it is possible to more effectively attract the driver's attention.

[0194] The effects of the present invention are not limited to those described above, and those skilled in the art will clearly understand from the following description other effects not mentioned.

[0195] The term "unit" as used in one or more implementations can refer to a software or hardware component such as an FPGA or ASIC, and the "unit" performs a specific function. However, the meaning of "unit" is not limited to software or hardware. A "unit" can be configured to reside in addressable memory or to be executed by one or more processors. Thus, by way of example, a "unit" includes components (such as software components, object-oriented software components, class components, and task components) as well as processes, functions, attributes, processes, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within components and "units" can be combined into a smaller number of components and "units," or further separated into additional components and "units." Furthermore, components and "units" can be implemented as one or more CPUs within an execution device or a secure multimedia card.

[0196] Although the invention has been described with reference to one or more exemplary embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as set forth in the claims.

Claims

1. An autonomous vehicle control device, comprising: processor; as well as A memory storing at least one instruction, which, when executed by a processor, is configured to cause the autonomous vehicle control device to: Identify the first piece of information related to the driver's attention state regarding the autonomous vehicle; Identify secondary information related to the surrounding road environment of autonomous vehicles; During the autonomous driving control of the autonomous vehicle, a reference value for setting the warning output conditions is determined based on the first information and the second information; The warning output of the autonomous vehicle is controlled based on the determined reference value.

2. The autonomous vehicle control device according to claim 1, wherein, The first information includes at least one of the following: the driver's line of sight, the driver's blink, the driver's head position change, or the driver's reaction time to a warning signal inside the vehicle.

3. The autonomous vehicle control device according to claim 1, wherein, The first information includes the results learned based on the driver's historical attention state data. The at least one instruction, when executed by the processor, is configured to cause the autonomous vehicle control device to determine the reference value in the following manner: Reference values ​​are determined by comparing the learning results with real-time data on the driver's attention state.

4. The autonomous vehicle control device according to claim 1, wherein, The at least one instruction, when executed by the processor, is configured to cause the autonomous vehicle control device to determine the reference value in the following manner: Identify third information related to the driver's biometric information; Further, a reference value is determined based on the aforementioned third information.

5. The autonomous vehicle control device according to claim 1, wherein, The at least one instruction, when executed by the processor, is configured to cause the autonomous vehicle control device to determine the reference value in the following manner: Reference values ​​are determined based on at least some information selected from the first information and the second information, based on changes in the driver's driving habits or the surrounding road environment.

6. The autonomous vehicle control device according to claim 1, wherein, The at least one instruction, when executed by the processor, is configured to further cause the autonomous vehicle control device to adjust the reference value in real time.

7. The autonomous vehicle control device according to claim 1, wherein, The at least one instruction, when executed by the processor, is configured to cause the autonomous vehicle control device to control the warning output of the autonomous vehicle in the following manner: The output includes a first warning, which is at least one of a visual warning, an auditory warning, or a tactile warning; Receive the driver's response to the first warning; Based on the driver's reaction, a second warning is output that is different from or a combination of different types of the first warning.

8. The autonomous vehicle control device according to claim 1, wherein, The surrounding road environment includes at least one of the following: The type of road the autonomous vehicle is traveling on; Traffic around autonomous vehicles; or Weather conditions in the area where the autonomous vehicle is driving.

9. The autonomous vehicle control device according to claim 1, wherein, The at least one instruction, when executed by the processor, is configured to cause the autonomous vehicle control device to control the warning output of the autonomous vehicle in the following manner: Based on reference values, adjust at least one of the types, cycles, modes, or intensities of warning outputs from autonomous vehicles.

10. The autonomous vehicle control device according to claim 1, wherein, The at least one instruction, when executed by the processor, is configured to cause the autonomous vehicle control device to control the warning output of the autonomous vehicle in the following manner: Information related to the control status of warning outputs is output via the input / output interface of the autonomous vehicle.

11. A method performed by a device of an autonomous vehicle, the method comprising: Identify the first piece of information related to the driver's attention state regarding the autonomous vehicle; Identify secondary information related to the surrounding road environment of autonomous vehicles; During the autonomous driving control of the autonomous vehicle, a reference value for setting the warning output conditions is determined based on the first information and the second information; The warning output of the autonomous vehicle is controlled based on the determined reference value.

12. The method according to claim 11, wherein, The first information includes at least one of the following: The driver's line of sight, the driver's blinking, changes in the driver's head direction, or the driver's reaction time to warning signals inside the vehicle.

13. The method according to claim 11, wherein, The first information includes the results learned based on the driver's historical attention state data. Determining reference values ​​includes: Reference values ​​are determined by comparing the learning results with real-time data on the driver's attention state.

14. The method according to claim 11, wherein, Determining reference values ​​includes: Identify third information related to the driver's biometric information; The reference value is determined based on the aforementioned third information.

15. The method according to claim 11, wherein, Determining reference values ​​includes: Reference values ​​are determined based on at least some information selected from the first information and the second information, based on changes in the driver's driving habits or the surrounding road environment.

16. The method according to claim 11, wherein, Warning outputs for controlling autonomous vehicles include: The output includes a first warning, which is at least one of a visual warning, an auditory warning, or a tactile warning; Receive the driver's response to the first warning; Based on the driver's reaction, a second warning is output that is different from or a combination of different types of the first warning.

17. The method according to claim 11, wherein, The surrounding road environment includes at least one of the following: The type of road the autonomous vehicle is traveling on; Traffic around autonomous vehicles; or Weather conditions in the area where autonomous vehicles are operating.

18. The method according to claim 11, wherein, Warning outputs for controlling autonomous vehicles include: Adjust at least one of the type, cycle, mode, or intensity of the warning output of the autonomous vehicle based on a reference value.

19. The method according to claim 11, wherein, Warning outputs for controlling autonomous vehicles include: Information related to the control status of warning outputs is output via the input / output interface of the autonomous vehicle.

20. An autonomous vehicle comprising: Sensors configured to detect the attentional state of the driver in an autonomous vehicle; processor; as well as A memory that stores at least one instruction, wherein the at least one instruction, when executed by a processor, is configured to cause the autonomous vehicle to: The sensor identifies the driver's initial state of attention in the first instant. During autonomous driving control of an autonomous vehicle, based on a first attention state, a first warning signal is output via the input / output interface of the autonomous vehicle, wherein the first warning signal has a first warning signal type; Determine the driver's reaction time to the first warning signal; The driver's second state of attention is identified via sensors at a later time than the first time. During autonomous driving control of the autonomous vehicle, based on a second attention state and based on the reaction time being greater than a threshold time, a second warning signal is output via the input / output interface of the autonomous vehicle, wherein the second warning signal has a second warning signal type that is different from the first warning signal type.

Images