Automatic driving vehicle and automatic driving method of vehicle

Abstract

A vehicle device includes a processor and a memory storing at least one instruction that, when executed by the processor in communication with the memory, is configured to cause the device to identify a potential target within a threshold distance from a vehicle, determine whether the vehicle is in a hazardous condition based on the potential target, and determine whether the vehicle is in the hazardous condition based on the determined potential target. It is determined whether a driver of the vehicle is negligible based on data from the vehicle sensor, and based on determining that the vehicle is in a hazardous condition and the driver is negligible, at least one output interface of the vehicle is controlled to output a warning signal to the driver.

Description

Technical Field

[0001] This disclosure relates to autonomous vehicles and autonomous driving methods for vehicles, and more specifically, to an autonomous vehicle and autonomous driving method for vehicles capable of preventing accidents caused by driver negligence in vehicles using driver assistance functions. Background Technology

[0002] The content described in this background section is only intended to enhance understanding of the background of this disclosure and should not be construed as an admission that it constitutes prior art known to those skilled in the art.

[0003] Autonomous vehicles may include an onboard terminal corresponding to an autonomous driving device, which is built into various vehicles and achieves autonomous driving by searching for the vehicle's location. Such autonomous driving devices are mainly used in ships, aircraft, and other vehicles on roads. For example, they can use displays to inform users of driving routes, traffic congestion, and other information, enabling the vehicle to drive autonomously or control its driving status.

[0004] Such autonomous vehicles can use driver assistance features for autonomous driving, such as SCC 2 (Intelligent Cruise Control 2) or HDA 2 (Highway Driving Assist 2).

[0005] However, since SCC 2 or HDA 2 does not offer fully automated driving capabilities, accidents may occur due to driver negligence (such as not paying attention to the road ahead). To prevent this problem, a separate function can be set up.

[0006] SCC 2 is a driver convenience feature that uses sensors such as front radar and a front camera to assist in identifying targets, maintaining a safe distance from the vehicle in front, and traveling at a speed set by the driver. When the in-vehicle camera determines that the driver is unresponsive, it can decelerate while maintaining lane centering and bring the vehicle to a stop within the lane, thus performing an emergency stop function.

[0007] HDA 2 is a driver convenience feature that assists in maintaining a safe distance from the vehicle in front when driving on highways and expressways. Even on curves, it helps keep the vehicle centered in its lane at a speed set by the driver. Using sensors such as front side radar, it can detect vehicles entering the current lane at low speed at close range; if an adjacent vehicle approaches, the vehicle will swerve to avoid danger. Furthermore, for user safety, a warning will be issued if the driver is not holding the steering wheel. If the user still does not hold the steering wheel, the HDA 2 function may be deactivated.

[0008] As mentioned above, SCC 2 and HDA 2 include preventative measures to prevent accidents caused by driver negligence. However, the following issues still exist.

[0009] To reduce excessive warnings to negligent drivers (e.g., not paying attention to the road ahead, not holding the steering wheel, etc.), the aforementioned driver assistance functions such as SCC 2 or HDA 2 may include a grace period for determining negligent behavior. Therefore, a warning will only be issued to the driver after the negligent behavior has continued for a certain period of time.

[0010] Therefore, if a driver repeatedly exhibits inattentiveness / negligence during the grace period (e.g., repeatedly gripping and not gripping the steering wheel), driver assistance features may continue to be used without a separate warning. This can lead to increased driver reliance on these features, resulting in decreased attention to the road ahead, potentially causing or increasing the risk of accidents. In fact, traffic accidents involving vehicles using driver assistance features and the resulting fatalities have been steadily increasing.

[0011] In addition, driver assistance functions may use various sensors such as front-facing cameras, front radar, and front and rear side radars to select control targets, so it is necessary to prevent functional failures caused by incorrect target detection.

[0012] Additionally, there may be time delays in selecting reliable targets for each sensor, and targets may not be identified due to hardware performance limitations associated with the sensors, such as in tunnels with many reflectors or in unexpected situations. Summary of the Invention

[0013] Therefore, this disclosure aims to provide an autonomous vehicle and an autonomous driving method for the vehicle, which substantially eliminates one or more problems caused by the limitations and disadvantages of related technologies.

[0014] This disclosure aims to solve the above-mentioned problems and provide an autonomous vehicle and an autonomous driving method for the vehicle, so as to reduce the risk of accidents caused by driver negligence when using driver assistance functions.

[0015] Other advantages, objects and features of this disclosure will be set forth in part in the description which follows, and in part will become apparent to those skilled in the art upon examination of the following, or may be learned from practice of this disclosure.

[0016] According to this disclosure, a vehicle device may include a processor and a memory storing at least one instruction, which, when executed by the processor in communication with the memory, is configured to cause the device to identify a potential target within a vehicle threshold distance, determine whether the vehicle is in a dangerous situation based on the potential target, determine whether the vehicle driver is negligent based on data from vehicle sensors, and control at least one output interface of the vehicle to output a warning signal to the driver based on the determination that the vehicle is in a dangerous situation and the driver is negligent.

[0017] In the device, at least one instruction, when executed by a processor communicating with a memory, is configured to enable the device to communicate with at least one of a front-facing camera, a front-facing radar, a front-side radar, or a navigation system, wherein the front-facing camera, the front-facing radar, the front-side radar, and the navigation system are mounted at the front of the vehicle.

[0018] In the device, at least one instruction, when executed by a processor communicating with a memory, is configured to enable the device to communicate with at least one of an in-vehicle camera or an audio-visual navigation system (AVN), wherein the in-vehicle camera and the AVN are installed inside the vehicle.

[0019] In this device, at least one instruction, when executed by a processor communicating with the memory, is configured to cause the device to control at least one of the vehicle's dashboard, the vehicle's steering wheel, or the vehicle's seat belt.

[0020] In this device, the criteria for identifying potential targets are less stringent than those used to identify control targets, and the control targets are objects selected using sensor fusion that have a higher confidence threshold than potential targets.

[0021] According to this disclosure, a method performed by a vehicle device may include: setting the vehicle to a user-defined mode based on determining that the vehicle driver is negligent; identifying a potential target within a threshold distance from the vehicle based on the user-defined mode; determining whether the vehicle is in a dangerous situation based on the potential target; and controlling at least one output interface of the vehicle to output a warning signal to the vehicle driver based on determining that the vehicle is in a dangerous situation.

[0022] The method may include: estimating the duration of the driver's negligence; guiding the driver to pay attention to the road ahead; and setting the vehicle to user-defined mode based on the duration exceeding a preset time.

[0023] In this method, the identification of potential targets may include using a front-side measuring device installed in the vehicle to identify potential targets, and the criteria for identifying potential targets are less stringent than those used to identify control targets.

[0024] In this method, control may include outputting a warning signal to the vehicle driver using at least one of the vehicle's dashboard, steering wheel, or seat belt.

[0025] In this method, the front measuring device is at least one of a vehicle's front-facing camera or front-facing radar, the controlled target is identified based on meeting a first reliability threshold, and the potential target is identified based on meeting a second reliability threshold lower than the first reliability threshold.

[0026] The method may further include: determining that the reliability value associated with the control target meets a first reliability threshold based on the consistency between the physical values ​​measured by the front-facing camera and the front-facing radar.

[0027] In this method, the physical values ​​include at least one of the longitudinal position of the detected object, the lateral position of the detected object, the speed of the detected object, or the heading angle of the detected object, wherein the detected object is the control target.

[0028] In this method, the identification of potential targets may include: determining a reliability value by applying weights to the lateral position of the controlled target or the lateral position of the potential target based on sensor measurement results, wherein the lateral position of the controlled target or the lateral position of the potential target is measured by the vehicle's front-facing camera.

[0029] In this method, the identification of potential targets may include: determining a reliability value by applying weights to the longitudinal position of the controlled target or the longitudinal position of the potential target based on sensor measurement results, wherein the longitudinal position of the controlled target or the longitudinal position of the potential target is measured by the vehicle's front radar.

[0030] In this method, the identification of potential targets may include: selecting another vehicle as a potential target based on the fact that another vehicle located in an adjacent lane of the vehicle's driving lane has intruded into the vehicle's driving lane by at least a first threshold amount.

[0031] In this method, the vehicle is traveling on a highway segment, and the potential target may include at least one of a congested area, a construction area, or an accident site, wherein each of the congested area, construction area, and accident site is identified based on information received from the vehicle's navigation system.

[0032] In this method, the potential target is an obstacle on the road where the vehicle is traveling.

[0033] In this method, the potential target is an obstacle on the road in which the vehicle is traveling, and the potential target is identified based on the avoidance driving action of the vehicle in front of the vehicle.

[0034] According to this disclosure, a vehicle device may include a processor and a memory storing at least one instruction, which, when executed by the processor in communication with the memory, is configured to cause the device to determine that the cumulative time of driver negligence exceeds a threshold time, based on the determination, set the vehicle to a user-defined mode, receive sensor data indicating the surrounding environment within a threshold distance from the vehicle, identify potential targets based on the sensor data, wherein the criteria used for identifying potential targets are less stringent than those used for identifying controlled targets, determine whether the vehicle is in a dangerous situation based on the potential targets, and, based on the determination that the driver is negligent and the vehicle is in a dangerous situation, control the vehicle's output devices to output a warning signal to the driver.

[0035] In the device, at least one instruction, when executed by a processor communicating with memory, is configured to cause the device to determine cumulative neglect time based on driver gaze information obtained from an in-vehicle camera, wherein driver negligence is determined based on the duration during which the driver does not look ahead exceeding a gaze threshold time, and the cumulative neglect time is increased based on the duration of the time exceeding the gaze threshold time.

[0036] It should be understood that the foregoing general description and the following detailed description of this disclosure are exemplary and explanatory, and are intended to provide further explanation of the claimed disclosure. Attached Figure Description

[0037] The accompanying drawings are provided to further illustrate the present disclosure and are incorporated in and constitute a part of this application. The drawings illustrate examples of the present disclosure and, together with the description, serve to explain the principles of the disclosure. In the drawings:

[0038] Figure 1 shows a configuration example of an autonomous vehicle according to the present disclosure;

[0039] Figure 2 illustrates an example of an autonomous driving method for a vehicle according to the present disclosure;

[0040] Figure 3 shows an example of creating a suspicious target as shown in Figure 2. Detailed Implementation

[0041] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the exemplary accompanying drawings. When adding reference numerals to the components in the various drawings, it should be noted that even if components are shown in different drawings, the same reference numerals should be assigned to the same components whenever possible. Furthermore, in describing embodiments of the present disclosure, detailed descriptions of related known structures or functions will be omitted if it is determined that such detailed descriptions would hinder understanding of the embodiments of the present disclosure.

[0042] In the description of embodiments according to this disclosure, when an element is described as being formed "above or below" another element, the two elements may be in direct contact or may be formed indirectly through one or more other elements disposed in between. Furthermore, when the expression "above or below" is used, the orientation of an element may include both an upward and a downward direction.

[0043] For the purposes of this application and claims, when the exemplary phrases “at least one: A; B; or C” or “at least one A, B, or C” are used, 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 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 refer to each of the listed items or all possible combinations of the listed 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.

[0044] In this disclosure, a "controller" can be implemented as a processor and memory. "Processor" should be interpreted broadly, including general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), microcontrollers, state machines, etc. In some cases, "processor" can refer to application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or field-programmable gate arrays (FPGAs). For example, "processor" can refer to a combination of processing devices, such as a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors and a DSP core, or any other such combination. Furthermore, "memory" should be interpreted broadly, including any electronic component capable of storing electronic information. "Memory" can refer to various types of processor-readable media, such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic or optical data storage devices, and registers. Memory can be in a state of electronic communication with the processor when the processor is able to read information from and / or record information to the memory. The memory integrated into the processor is in electronic communication with the processor.

[0045] In order to be executable on a computer, one or more of the features described herein can be stored as a computer program on a computer-readable recording medium. This medium can persistently store a computer-executable program or temporarily store a program for execution or download. Furthermore, the medium can be a variety of recording or storage devices in the form of a single hardware device or multiple combined hardware devices, and is not limited to media directly connected to certain computer systems, but can also be distributed over a network. Examples of such media include magnetic media (such as hard disks, floppy disks, or magnetic tapes), optical recording media (such as CD-ROMs or DVDs), magneto-optical media (such as floppy disks), and ROM, RAM, or flash memory configured to store program instructions. Other examples of such media include media or storage media managed by application stores that distribute applications or various other websites or servers that provide or distribute software.

[0046] According to the classification standards of the Society of Automotive Engineers (SAE), the automation levels of autonomous vehicles can be divided into the following categories. Level 0 automation corresponds to "no automation" in the SAE classification, meaning the autonomous driving system only intervenes temporarily in emergency situations (e.g., automatic emergency braking) and / or only provides warnings (e.g., blind spot warning, lane departure warning, etc.), and the driver is responsible for vehicle operation. Level 1 automation corresponds to "driver assistance" in the SAE classification, where the system performs some driving functions (e.g., steering, acceleration, braking, lane centering, adaptive cruise control, etc.), while the driver is responsible for driving the vehicle during normal operation, and needs to assess the system's operating status and / or timing, perform other driving functions, and respond to (e.g., handle) emergency situations. Level 2 automation corresponds to "partial automation" in the SAE classification, where the system performs steering, acceleration, and / or braking under the driver's supervision, and the driver needs to assess the system's operating status and / or timing, perform other driving functions, and respond to (e.g., handle) emergency situations. In Level 3 autonomous driving, the SAE classification corresponds to "conditional automation." The system drives the vehicle under limited conditions (e.g., performing driving functions such as steering, acceleration, and / or braking), but when the required conditions are not met, it returns driving control to the driver. The driver needs to assess the system's operating status and / or timing, and take over control in emergencies. Otherwise, no further vehicle operation is required (e.g., steering, acceleration, and / or braking). In Level 4 autonomous driving, the SAE classification corresponds to "high automation." The system performs all driving functions, and the driver only needs to take over vehicle control in emergencies. In Level 5 autonomous driving, the SAE classification corresponds to "full automation." The system performs all driving functions in all scenarios, including emergencies, without any driver assistance. The driver only needs to assess the system's operating status and does not need to perform any driving functions. Although this disclosure uses the SAE classification to classify autonomous driving, other classification methods and / or algorithms may also be used in one or more configurations described herein.

[0047] One or more functions related to autonomous driving control can be activated based on configured autonomous driving control settings (e.g., based on at least one of the following: autonomous driving classification, selection of vehicle autonomous driving level, etc.). Based on one or more functions described herein (e.g., functions that identify potential targets and determine that the vehicle is in a dangerous situation), the operation of the vehicle can be controlled. Vehicle control may include various operational controls related to the vehicle (e.g., autonomous driving control, sensor control, braking control, braking time control, acceleration control, rate of change of acceleration control, warning timing control, forward collision warning time control, etc.).

[0048] One or more auxiliary devices (e.g., engine brakes, exhaust brakes, hydraulic retarders, electric retarders, regenerative brakes, etc.) may also be controlled based on one or more functions described herein (e.g., the function of identifying potential targets and determining that the vehicle is in a dangerous situation). 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, including 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 based on one or more functions described herein (e.g., the function of identifying potential targets and determining that the vehicle is in a dangerous situation).

[0049] Minimum Risk Maneuvering (MRM) can also be controlled based on one or more functions described herein, such as functions that identify potential targets and determine that the vehicle is in a hazardous situation. Minimum Risk Maneuvering (e.g., minimum risk control, lowest risk control) is a maneuver undertaken by the vehicle to achieve a reduced (e.g., minimum) risk state, aimed at minimizing (e.g., reducing) the risk of collision with surrounding vehicles. Minimum Risk Control can refer to an operation activated during autonomous driving when the driver is unable to respond to an intervention request. During Minimum Risk Control, one or more processors in the vehicle can control the vehicle's driving operations for a set period of time.

[0050] Lane departure control can also be controlled based on one or more of the functions described herein (e.g., functions that identify potential targets and determine if the vehicle is in a dangerous situation). The driving control unit can perform lane departure control. To achieve lane departure control, the driving control unit controls the vehicle to travel within the lane by maintaining a lateral distance between the vehicle's center position and the lane center. For example, the driving control unit can control the vehicle to remain within the lane but not in the lane center position. The driving control unit can identify or determine a target lateral distance for lane departure control. For example, the target lateral distance may include the lateral distance that the vehicle intentionally adjusts to maintain distance from a reference point (such as the lane center or other vehicles) during maneuvers such as lane changes. This adjustment can improve the vehicle's stability, safety, and / or performance under different driving conditions. For example, during a lane change, the driving control system can consider factors such as vehicle speed, road conditions, and / or the presence of obstacles to shift the lateral distance to maintain a safer distance from adjacent vehicles.

[0051] One or more sensors (e.g., IMU sensor, camera, lidar, radar, blind spot monitoring sensor, lane departure warning sensor, parking sensor, light sensor, rain sensor, traction control sensor, anti-lock braking system sensor, tire pressure monitoring sensor, seat belt sensor, airbag sensor, fuel sensor, emission sensor, throttle position sensor, inverter, converter, motor controller, power distribution unit, high-voltage lines and connectors, auxiliary power module, charging interface, etc.) may also be controlled based on one or more functions described herein (e.g., the function of identifying potential targets and determining that the vehicle is in a dangerous situation). The operational control of autonomous driving may include various driving controls performed on the vehicle by the vehicle control unit (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, etc.).

[0052] The autonomous vehicle and autonomous driving method of the vehicle described in this disclosure use driver assistance functions, which can relax existing control target selection conditions to generate new suspicious targets when the driver is negligent during driving (e.g., not holding the steering wheel or not paying attention to the road ahead); and issue separate warnings to attract the driver's attention when a suspicious target is identified or a dangerous situation is detected.

[0053] Figure 1 shows an example configuration of an autonomous vehicle according to an example of the present disclosure. Figure 2 shows an example of an autonomous driving method for a vehicle according to an example of the present disclosure. Figure 3 shows an example of creating a suspicious target in Figure 2. Hereinafter, examples of the autonomous vehicle and the autonomous driving method for the vehicle described in this disclosure will be described in conjunction with Figures 1, 2, and 3.

[0054] Examples of autonomous vehicles and autonomous driving methods for vehicles described in this disclosure may include vehicles and driving methods that use driver assistance functions.

[0055] Referring to FIG1, an autonomous vehicle may include a controller configured to perform driver assistance functions, the controller including: a first controller 100 configured to generate suspicious targets and determine dangerous situations; a second controller 200 configured to determine the operating status of the functions or determine whether the driver is negligent; and a third controller 300 configured to, for example, issue a warning to the driver in response to a dangerous situation.

[0056] The first controller 100 can communicate with each of the front-facing camera 110, front-facing radar 120, front side radar 130, and navigation system 140 included in the vehicle (e.g., for detecting objects ahead, monitoring lane incursions, identifying static obstacles, or identifying hazardous road sections). The second controller 200 can communicate with each of the in-vehicle camera 210 and audio-visual navigation system (AVN) 220 included in the vehicle (e.g., for monitoring the driver's gaze direction, assessing attention, displaying warnings, or providing audio-visual warnings). The third controller 300 can communicate with each of the instrument panel 310, steering wheel 320, and seat belt 330 (e.g., via haptic feedback, tightening actions, or audio-visual instructions).

[0057] The following describes a method for driving a vehicle using driver assistance functions by installing a controller with the above configuration in the vehicle (e.g., for managing target recognition, driver monitoring, and hazard warnings).

[0058] First, the vehicle can be driven with driver assistance functions activated (S110). Here, driver assistance functions can be, for example, SCC 2 or HDA 2 (e.g., for maintaining distance from the vehicle in front, assisting in lane centering, or controlling vehicle speed on highways or curves).

[0059] Then, the vehicle is set to User-Defined Mode (USM), and it is determined whether the vehicle is set to USM-enabled state (S120). Here, USM refers to the operation of generating and identifying suspicious targets (e.g., based on a reduced sensor reliability threshold, radar-only detection, or partial lane intrusion, etc.) during the operation of driver assistance functions, in addition to other control objectives.

[0060] If the USM is on (yes), it is determined whether the driver is negligent (S130). When determining whether the driver is negligent, for example, the driver's gaze information is identified by the in-vehicle camera 210 installed inside the vehicle. When it is determined that the driver is not paying attention to the road ahead, it is considered that the driver is negligent (yes), and the generation of a suspicious target is triggered (S140) (e.g., due to prolonged deviation of gaze, closed eyes, or head tilted downwards).

[0061] If it is determined that the driver is paying attention to the road ahead and there is no negligence (No), the vehicle can activate the driver assistance function and continue driving (S110) without activating the USM logic.

[0062] If the vehicle is not set to USM active (No), a process is performed to determine whether the driver is driving carelessly (e.g., by assessing the direction of the gaze, lack of steering action, or inattention). More specifically, the driver's cumulative neglect time is calculated (S122), and it is determined whether the driver's cumulative neglect time exceeds, for example, a preset time (e.g., 5 minutes, 10 minutes, or 15 minutes) (S124). Here, the aforementioned in-vehicle camera 210 can be used to determine whether the driver is negligent (e.g., by monitoring intermittent inattention, failure to concentrate, or repeated disengagement from steering operations).

[0063] If the driver's cumulative time of negligence does not exceed, for example, 10 minutes (No), the vehicle can activate the driver assistance function and continue driving (S110). If the driver's cumulative time of negligence exceeds, for example, 10 minutes (Yes), the driver is informed to pay attention to the road ahead, and the vehicle is switched to USM activation state (S126).

[0064] In this situation, the AVN 220 described above can be used to inform the driver, for example, through the vehicle's audio or video (display screen) or navigation system; when using a video or navigation system, the driver can be informed via a modal dialog box (e.g., with a warning icon, pop-up message, or sound notification). Here, the content provided to the driver could be a message indicating that the vehicle has switched to USM activation and that even when using such driver assistance features, the driver needs to continue to pay attention to the road ahead.

[0065] Through the above process, driver assistance functions can be used. If the driver's negligence time accumulates to a certain duration, the following functions can be activated by automatically switching to the USM on state (e.g., enabling suspicious target generation or enhancing hazard detection).

[0066] Next, the process of generating a suspicious target and using that suspicious target to warn the driver (e.g., through visual, auditory, or tactile alerts) will be explained.

[0067] In driver assistance functions, the criteria for selecting control targets (e.g., other vehicles in front of the vehicle or cargo on the highway) can be lowered by using a front camera, front radar, and front side radar to select monitoring targets. These monitored targets are referred to as "suspicious targets" (e.g., slow-moving vehicles, vehicles stopped in tunnels, or fallen objects).

[0068] For example, if the setting standard for control targets is higher than the first reliability, then the generation standard for suspicious targets can be set to the second reliability. In this way, targets that were not previously identified as control targets can be selected as suspicious targets and monitored. In this case, the first reliability can be 40, and the second reliability can be in the range of 30 to 40.

[0069] The "reliability" mentioned here refers to, for example, the high reliability if the consistency between the physical values ​​measured by the front camera and the front radar is higher than a threshold (e.g., if the two sensors measure the object's speed, position, and heading angle of the vehicle in the same way).

[0070] The process of generating suspicious targets around a moving vehicle (S140) may include the following steps: relaxing the reliability criteria for target selection through sensor fusion (S142); changing the identification method of static targets from sensor fusion to a single forward layer (S146) (e.g., based on a single front radar); and relaxing the criteria for determining targets that intrude into the vehicle's lane (S148) (e.g., reducing the lateral intrusion threshold from 50% to 10%).

[0071] The following details the process of relaxing the reliability criteria for target selection through sensor fusion.

[0072] The method for selecting a target using sensors is as follows. For example, if the consistency of the physical quantities (such as longitudinal position, lateral position, speed, heading angle, acceleration, etc.) measured by the various front measuring devices (such as front camera 110, front radar 120, front radar 130, etc.) of a vehicle traveling toward a target is higher than a threshold, then its reliability can be determined to be high (for example, when the position error range of different types of sensors is within the specified threshold, this is the case).

[0073] In this example, the reliability criteria for selecting targets through sensor fusion are relaxed (S142). Specifically, instead of simply adding up the reliability of suspicious targets calculated by each sensor, each reliability can be weighted based on directional accuracy or sensor characteristics before being added together.

[0074] For example, front-facing radar has an advantage in longitudinal recognition, so it can be weighted when selecting the longitudinal position of a target (e.g., for detecting distance to a vehicle or identifying a stopped object ahead). Furthermore, front-facing cameras have an advantage in lateral recognition, so they can be weighted when selecting the lateral position of a target (e.g., for distinguishing objects in the adjacent lane, road markings, or adjacent vehicles).

[0075] Additionally, targets outside the range that each sensor cannot detect may be excluded from the reliability selection and therefore will not be selected as suspicious targets (e.g., objects beyond the sensor's range, occluded targets, or targets in the sensor's blind zone). Furthermore, the criteria for selecting a target as a suspicious target may be relaxed compared to other control targets, for example, by expanding the detection range in cases of edges or blurriness.

[0076] For moving targets (such as the vehicle in front), the above method can be used to determine whether the target is suspicious based on the measurements from the front radar and the front camera (e.g., when the vehicle suddenly decelerates or cuts into another lane). However, the method for identifying static targets can be changed as follows (S146).

[0077] For example, in sensor fusion, where decisions are based on measurements from multiple sensors, decisions can be made based on measurements from a single sensor. While sensor fusion can improve accuracy, it can become difficult to select targets if the large number of sensor measurements leads to excessively long selection times or significant discrepancies between the measurements. Therefore, even with reduced accuracy, suspicious targets can be selected based on a single measurement from a single sensor (such as the forward-facing radar 120) (e.g., for faster detection of static obstacles in tunnels or near construction areas).

[0078] Furthermore, the criteria for determining a vehicle that intrudes into the lane can be dynamically relaxed, for example, based on factors such as driving environment, sensor confidence, or driver attention (S148). For instance, when another vehicle changes lanes from an adjacent lane and intrudes into the driving lane from the front or side of the vehicle, previously it would be selected as a control target if the intrusion amounted to 50%, but now it can be selected as a suspicious target if the intrusion exceeds a smaller threshold (such as a first value). Here, the first value can be 10%. The 50% intrusion and 10% intrusion here refer to the proportion of other vehicles' lateral width intruding into the lane being 50% and 10%, respectively (e.g., due to sudden lane changes, emergency merging, or lane deviation during overtaking).

[0079] Using the above method, the first controller 100 generates a suspicious target (S140), and the first controller 100 can determine the dangerous situation (e.g., based on distance, movement trend or relevant navigation data).

[0080] The determination of a dangerous situation can be made when a suspicious target is selected as described above, or based on a specific scenario in steps S160 to S180 below (e.g., a dangerous area on a highway, road debris, or a sudden lane intrusion). Furthermore, if a suspicious target is identified (S150) or other dangerous situations are determined to exist (S160 to S180), a warning (S190) can be issued (e.g., immediately or in real time) to remind the driver to remain vigilant (e.g., through visual, auditory, or tactile feedback). As described below, a warning can be issued by sending a hazard warning signal to the instrument panel 310, steering wheel 320, or seatbelt 330 via the third controller 300 (e.g., through multi-modal feedback to re-attract the driver's attention).

[0081] First, regarding the identification of suspicious targets (S150), it can be determined whether a suspicious target has been identified by the following methods (S150): relaxing or lowering the reliability threshold used for target selection through sensor fusion (S142); identifying stationary targets using only the forward layer (S146) (e.g., a single forward sensor); or relaxing the criteria for determining targets that intrude into the vehicle's lane as described above (S148) (e.g., based on partial intrusion or sudden lateral movement). When a suspicious target is identified (yes), a warning can be issued to the driver in real time (S190).

[0082] As described above, warnings to the driver can be issued by: stimulating the driver's vision or hearing by displaying a warning on the screen or by emitting a warning sound on the instrument panel 310; stimulating the driver's tactile sense by vibrating the steering wheel 320; or stimulating the driver's tactile sense in the waist or shoulders by tightening the seat belt 330 (e.g., by using a seat belt pretensioner).

[0083] The following is a specific example of suspicious target identification.

[0084] First, dangerous sections of highways (S160) can be identified. For example, it can be determined whether a vehicle is traveling on a dangerous section of a highway or a dedicated vehicle lane. However, the determination method may vary depending on whether the vehicle's navigation system is operational (e.g., based on real-time data or the availability of map hazardous areas).

[0085] For example, if the navigation system installed in the vehicle is operational, real-time road traffic information from the navigation system can be used to identify dangerous sections of the highway. For instance, congested areas (red zones), construction zones, accident sites, lane closures, or speed enforcement zones can be identified as dangerous sections of the highway. Furthermore, based on the navigation system information, if a dangerous section is determined to exist a few kilometers (km) ahead of the driving route, it can be identified as a hazardous situation requiring the driver's attention.

[0086] If the navigation system of the vehicle is not running and there is no navigation information, when the suspicious target generated by the above-mentioned suspicious target generation method (S140) is identified, it can be determined that there is a dangerous section of the highway (e.g., inferred from detected obstacles or abnormal vehicle behavior).

[0087] The above method is used to determine whether the vehicle is in a dangerous section of the highway (S160). When it is determined that the vehicle is in a dangerous section of the highway (yes), the above method can be used to issue a warning to the driver (S190) (e.g., through a warning pop-up, audible alarm or tactile feedback).

[0088] In addition, it can be determined whether there are obstacles such as fallen goods on the road (S170). For example, the presence of a dangerous situation can be determined by whether there are obstacles such as fallen goods in front of the driving vehicle. However, the determination method may vary depending on whether there is a vehicle in front of the driving vehicle. Here, obstacles may include not only goods fallen from other vehicles, but also facilities in construction areas, road debris, parked vehicles, etc.

[0089] When there is falling cargo in front of a vehicle, the vehicle in front may take swerving maneuvers to avoid it (e.g., sudden lane change, continuous lateral deviation, or sharp departure). For example, if the change in the lateral position of the vehicle in front exceeds a certain value within a certain period of time, the maneuver can be determined to be swerving to avoid falling cargo (e.g., turning left or right beyond a threshold distance within a few seconds). Therefore, using information collected by the front-facing camera 110 or front-facing radar 120 installed in the vehicle, when an swerving maneuver is detected to avoid falling cargo (e.g., based on a sudden lateral departure or change in trajectory), a dangerous situation can be determined to exist.

[0090] If there is no vehicle in front of the driving vehicle, the driving action of avoiding falling cargo cannot be identified based on the behavior of the vehicle in front. Therefore, when falling cargo is generated and identified as a suspicious target by the above-mentioned suspicious target generation method (S140), it can be determined that the road is a dangerous section with falling or already fallen cargo (yes), and the above-mentioned method can be used to issue a warning to the driver (S190) (for example, through instrument panel display, steering wheel haptic feedback, or seat belt tightening).

[0091] In addition, it can be determined whether a vehicle is entering the lane in front of the vehicle (the lane in which the vehicle is traveling) (S180) (e.g., due to forced entry, lane change without signaling, or rapid approach from an adjacent lane).

[0092] For example, the first controller 100 uses information received from the front radar 120 or the front side radar 130 to calculate the relative position, speed, acceleration and lateral displacement trend of the vehicle in front in the adjacent lane of the driving lane. When the vehicle in front in the adjacent lane makes a move to quickly approach the driving lane (for example, suddenly laterally intruding or quickly merging), the driving vehicle can use the information received above to determine that there is a dangerous situation (yes) and issue a warning to the driver in the manner described above (S190).

[0093] In this situation, if the relative position change rate and speed change of the vehicle in front (especially the lateral position change rate or speed change) are greater than or equal to a certain value, it can be determined that the vehicle is rapidly entering the lane of the vehicle, and a warning can be issued to the driver before the potential collision risk increases (S190).

[0094] The objectives and other advantages of this disclosure are realized and achieved through the written description, the appended claims, and the structures particularly pointed out in the drawings. To achieve these objectives and other advantages, and in accordance with the spirit of this disclosure, as embodied and broadly described herein, an autonomous vehicle includes: a first controller configured to generate a suspicious target in front of the vehicle and determine a dangerous situation; a second controller configured to determine whether the driver of the vehicle is negligent; and a third controller configured to issue a warning to the driver when the vehicle is determined to be in a dangerous situation and the driver is negligent.

[0095] The first controller can communicate with at least one of a front-facing camera, front-facing radar, front side radar, or navigation system installed in front of the vehicle.

[0096] The second controller can communicate with at least one of the in-vehicle cameras or AVN (audio-visual navigation system) installed in the moving vehicle.

[0097] The third controller can communicate with at least one of the dashboard, steering wheel, or seat belt.

[0098] The criteria for generating suspicious targets can be lower than the criteria for setting controlled targets.

[0099] In another example of this disclosure, an autonomous driving method for a vehicle includes: setting the vehicle to a user-defined mode (USM); generating suspicious targets around the vehicle; determining whether the vehicle is in a dangerous situation based on the generated suspicious targets; and issuing a warning to the vehicle driver if the vehicle is in a dangerous situation.

[0100] The above settings may include: calculating the driver's negligence time; if the driver's negligence time exceeds a preset time, guiding the driver to pay attention to the road ahead and activating USM.

[0101] The above generation may include: generating suspicious targets using a front-side measuring device installed in the vehicle, wherein the generation criteria for suspicious targets are lower than the setting criteria for control targets.

[0102] The aforementioned warnings may include: issuing a warning to the vehicle driver using at least one of the dashboard, steering wheel, or seat belt.

[0103] The front-side measuring device can be at least one of a front-facing camera or a front-facing radar. The setting standard for the controlled target can be greater than or equal to the first reliability, and the generation standard for the suspicious target can be the second reliability.

[0104] If the consistency between the physical values ​​measured by the front-facing camera and the front-facing radar is greater than a threshold, then the reliability can be determined to be high.

[0105] Physical values ​​may include at least one of the longitudinal position, lateral position, speed, or heading angle of the controlled or suspected target.

[0106] When determining reliability, weights can be assigned to the lateral position of the controlled or suspected target measured by the front-facing camera.

[0107] When determining reliability, weights can be assigned to the longitudinal position of the controlled or suspected target measured by the forward radar.

[0108] Generating suspicious targets around a vehicle may include: if the amount of other vehicles in adjacent lanes encroaching on the lane of this vehicle reaches or exceeds a first value, then the vehicle is selected as a suspicious target.

[0109] Vehicles may travel on highways, and suspicious targets may include at least one of the following: congested areas, construction areas, or accident sites, as indicated by the vehicle's navigation system.

[0110] Suspicious targets can be obstacles on the road where vehicles travel.

[0111] A suspicious target can be an obstacle on the road in which the vehicle is traveling, and the suspicious target can be generated based on the avoidance driving action of the vehicle in front of it.

[0112] In another example of this disclosure, a program is recorded on a computer-readable recording medium, wherein the aforementioned autonomous driving method for the vehicle is executed by a processor.

[0113] In another example of this disclosure, a computer-readable recording medium stores the above-described program.

[0114] According to the above-described autonomous vehicle and autonomous driving method of the vehicle, when the driver is negligent while using the driver assistance function, the existing control target selection conditions will be relaxed to generate a new suspicious target; when a suspicious target is identified and a dangerous situation is determined, a warning will be issued to attract the driver's attention, thereby reducing the risk of an accident.

[0115] In the foregoing description, even though all components included in the examples of this disclosure are described as being combined or operating in combination, this disclosure is not necessarily limited to these examples. For example, within the scope of the purpose of this disclosure, all components may be selectively combined into one or more and operated. Furthermore, unless expressly stated otherwise, the terms “comprising,” “including,” or “having” above mean that the corresponding component may be included, and should therefore be interpreted as including rather than excluding other components. All terms (including technical or scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains, unless otherwise defined. Common terms (such as those defined in a dictionary) should be interpreted as having the meaning consistent with their meaning in the relevant field context and should not be interpreted in an idealized or overly formalized manner unless explicitly defined in this disclosure.

[0116] The above description is merely an exemplary illustration of the technical concept of this disclosure, and those skilled in the art can make various modifications and changes without departing from the essential characteristics of this disclosure. Therefore, the examples disclosed in this disclosure are not intended to limit the technical concept of this disclosure, but rather to describe it, and the scope of the technical concept of this disclosure is not limited by these examples. The scope of protection of this disclosure should be interpreted by the following claims, and all technical concepts within the equivalent scope should be interpreted as included within the scope of the rights of this disclosure.

Claims

1. A vehicle device, the device comprising: processor; as well as A memory storing at least one instruction, which, when executed by a processor communicating with the memory, is configured to cause the device to: Identify potential targets within a threshold distance of the vehicle. Based on the potential target, determine whether the vehicle is in a dangerous situation. Based on data from the vehicle's sensors, determine whether the vehicle's driver was negligent, and Based on the determination that the vehicle is in a dangerous situation and that the driver is negligent, control at least one output interface of the vehicle to output a warning signal to the driver.

2. The apparatus according to claim 1, wherein, When executed by the processor communicating with the memory, the at least one instruction is configured to enable the device to communicate with at least one of a front-facing camera, a front-facing radar, a front-side radar, or a navigation system, wherein the front-facing camera, the front-facing radar, the front-side radar, and the navigation system are mounted at the front of the vehicle.

3. The apparatus according to claim 1, wherein, When executed by the processor communicating with the memory, the at least one instruction is configured to enable the device to communicate with at least one of an in-vehicle camera or an audio-visual navigation system (AVN), wherein the in-vehicle camera and the AVN are installed in the vehicle.

4. The apparatus according to claim 1, wherein, When executed by the processor communicating with the memory, the at least one instruction is configured to cause the device to control at least one of the vehicle's dashboard, the vehicle's steering wheel, or the vehicle's seat belts.

5. The apparatus according to claim 1, wherein, The criteria for identifying potential targets are less stringent than those used to identify control targets, and the control targets refer to objects selected using sensor fusion that have a higher confidence threshold than the potential targets.

6. A method performed by a vehicle device, the method comprising: Based on the determination that the driver of the vehicle was negligent, the vehicle is set to user-defined mode. Based on the user-defined mode, identify potential targets within a threshold distance of the vehicle; Based on the potential target, determine whether the vehicle is in a dangerous situation; as well as Based on the determination that the vehicle is in a dangerous situation, control at least one output interface of the vehicle to output a warning signal to the driver of the vehicle.

7. The method according to claim 6, wherein, Setting the vehicle to the user-defined mode includes: Estimate the duration of the driver's negligence; Guide the driver to pay attention to what is ahead of the vehicle; and If the duration exceeds a preset time, the vehicle will be set to the user-defined mode.

8. The method according to claim 6, wherein, The identification of the potential target includes using a front-side measuring device installed in the vehicle to identify the potential target, and the criteria for identifying the potential target are less stringent than those used to identify control targets.

9. The method according to claim 6, wherein, Controlling at least one output interface of the vehicle to output a warning signal to the driver of the vehicle includes outputting the warning signal to the driver of the vehicle using at least one of the vehicle's dashboard, the vehicle's steering wheel, or the vehicle's seat belt.

10. The method according to claim 8, wherein: The front measuring device is at least one of the vehicle's front-facing camera or the vehicle's front-facing radar, and The control target is identified based on meeting a first reliability threshold, and the potential target is identified based on meeting a second reliability threshold lower than the first reliability threshold.

11. The method of claim 10, further comprising: Based on the consistency between the physical values ​​measured by the front-facing camera and the front-facing radar, it is determined that the reliability value associated with the control target meets the first reliability threshold.

12. The method according to claim 11, wherein, The physical values ​​include at least one of the longitudinal position of the detected object, the lateral position of the detected object, the speed of the detected object, or the heading angle of the detected object, wherein the detected object is the control target.

13. The method according to claim 8, wherein, The identification of potential targets includes: Based on sensor measurement results, a reliability value is determined by applying weights to the lateral position of the controlled target or the lateral position of the potential target, wherein the lateral position of the controlled target or the lateral position of the potential target is measured by the vehicle's front-facing camera.

14. The method according to claim 8, wherein, The identification of potential targets includes: Based on sensor measurements, a reliability value is determined by applying weights to the longitudinal position of the controlled target or the longitudinal position of the potential target, wherein the longitudinal position of the controlled target or the longitudinal position of the potential target is measured by the vehicle's front radar.

15. The method according to claim 8, wherein, The identification of the potential target includes: selecting the other vehicle as the potential target based on the fact that the amount of another vehicle located in the adjacent lane of the vehicle's driving lane intrudes into the vehicle's driving lane reaches at least a first threshold.

16. The method of claim 6, wherein: The vehicle was traveling on a highway section, and The potential targets include at least one of a congested area, a construction area, or an accident site, wherein each of the congested area, the construction area, and the accident site is identified based on information received from the vehicle's navigation system.

17. The method according to claim 8, wherein, The potential target is an obstacle on the road in which the vehicle is traveling.

18. The method according to claim 8, wherein: The potential target is an obstacle on the road in which the vehicle is traveling, and The potential target is identified based on the evasive maneuvers of the vehicle ahead traveling in front of the vehicle.

19. A vehicle apparatus, the apparatus comprising: processor; as well as A memory storing at least one instruction, which, when executed by a processor communicating with the memory, is configured to cause the device to: It was determined that the driver's cumulative time of negligence for the vehicle exceeded a threshold time. Based on the determination that the driver's cumulative time of negligence exceeds a threshold time, the vehicle is set to the user-defined mode. Receive sensor data indicating the surrounding environment within a threshold distance of the vehicle. Based on the sensor data, potential targets are identified, wherein the criteria used for identifying the potential targets are less stringent than those used for identifying control targets. Based on the potential target, determine whether the vehicle is in a dangerous situation, and Based on the determination that the driver is negligent and the vehicle is in a dangerous situation, the system controls the vehicle's output device to output a warning signal to the driver.

20. The apparatus according to claim 19, wherein, When executed by the processor communicating with the memory, the at least one instruction is configured to cause the device to determine the cumulative neglect time based on the driver's gaze information obtained from an in-vehicle camera. Specifically, if the driver's period of not looking ahead exceeds a visual threshold time, it is determined that the driver is negligent, and The cumulative neglect time is increased based on the duration of time exceeding the sight threshold.

Images