Driving assistance system and driving assistance method for a vehicle
The driving assistance system uses gaze and head position analysis to differentiate between intentional and unintentional lane changes, enhancing reliability and safety by minimizing disruptive warnings and interventions.
Patent Information
- Application Number
- PCT/EP2024/063263
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-26
- Filing Date
- 2024-05-14
- Publication Date
- 2024-12-05
AI Technical Summary
Existing driving assistance systems for vehicles, such as lane keeping assistants, often mistakenly identify intentional lane changes as unintentional, leading to disruptive warnings and interventions that can frustrate drivers and increase the likelihood of the system being switched off, compromising safety.
A driving assistance system that utilizes a recognition module to detect lane changes and an analysis module to categorize them as intentional or unintentional based on the driver's gaze behavior and head position, using data from interior sensors like cameras and infrared sensors, to avoid unnecessary warnings and interventions.
Improves the reliability of driving assistance systems by accurately distinguishing between intentional and unintentional lane changes, reducing unwanted interventions and increasing driver satisfaction and safety by preventing the system from being switched off.
Smart Images

Figure EP2024063263_05122024_PF_FP_ABST
Abstract
Description
[0001] Driver assistance system and driver assistance procedure for a vehicle
[0002] The present disclosure relates to a driver assistance system for a vehicle, a vehicle having such a driver assistance system, a driver assistance method for a vehicle, and a storage medium for executing the driver assistance method. In particular, the present disclosure relates to distinguishing between intended lane changes and unintentional lane changes.
[0003] State of the art
[0004] Driver assistance systems for vehicles are becoming increasingly important. One example of a driver assistance system is the lane departure warning system, which supports the driver in ensuring that the vehicle does not leave its ego lane. To do this, the driver assistance system records the lane path and, optionally, other parameters such as vehicle speed, steering angle and turn signal activation. If the vehicle leaves its ego lane, e.g. without activating the turn signals, the lane departure warning system issues a warning to the driver and / or intervenes directly in the vehicle guidance by means of active steering intervention in order to keep the vehicle in the ego lane. In this case, the driver and the lane departure warning system may work against each other, which can be unpleasant for the driver and, if it occurs frequently, can lead to the system being deactivated and thus poses risks in traffic.
[0005] Disclosure of the invention
[0006] It is an object of the present disclosure to provide a driver assistance system for a vehicle, a vehicle with such a driver assistance system, a driver assistance method for a vehicle, and a storage medium for executing the driver assistance method, which can improve the reliability of the driver assistance system, in particular a lane keeping assistance system. Furthermore, it is an object of the present disclosure to increase road safety.
[0007] This object is achieved by the subject matter of the independent claims. Advantageous embodiments are specified in the subclaims.
[0008] According to an independent aspect of the present disclosure, a driver assistance system for a vehicle, in particular a motor vehicle, is specified. The driver assistance system comprises a detection module configured to detect a lane change initiated by a driver; an interior sensor system configured to detect the driver and output corresponding detection data; an analysis module configured to determine a driver's gaze behavior based on the detection data and, based on the gaze behavior, to categorize the detected lane change into an intended (or conscious) lane change or an unintentional (or unconscious) lane change; and at least one control module configured to control at least one vehicle function based on the categorization of the detected lane change.
[0009] According to the invention, the driver's gaze behavior and / or head position are used to distinguish between an intentional or conscious lane change and an unintentional or unconscious lane change. The driver assistance system controls the at least one vehicle function, such as a lane keeping assistance function, based on this distinction, so that, for example, warnings and / or steering interventions that are disruptive to the driver can be avoided. As a result, the reliability of the driver assistance system can be improved and road safety increased, since the driver is not tempted to deactivate the system due to unwanted interventions.
[0010] The detection module and / or the analysis module and / or the at least one control module can be implemented in a common software and / or hardware module. Alternatively, the detection module and / or the analysis module and / or the at least one control module can each be implemented in separate software and / or hardware modules.
[0011] The term “categorization” as used in the present disclosure refers to an assignment of the lane change into the predefined categories “intentional lane change” and “unintentional lane change” based on the driver’s gaze behavior and optionally other factors.
[0012] The categorization can be carried out by means of software that processes input data (i.e. the detection data of the interior sensors and optionally further data, such as sensor data or a navigation route) in the real operation of the vehicle in order to recognize whether the detected lane change is an intentional or conscious lane change or an unintentional or unconscious lane change.
[0013] The driver assistance system's detection module is configured to detect a driver-initiated lane change. The lane change can be initiated, for example, by a manual action by the driver, in particular a steering movement away from the driver's own lane.
[0014] The detection module preferably uses acquisition data from at least one sensor module to detect the lane change initiated by the driver. The at least one sensor module can, for example, comprise at least one camera, in particular at least one exterior camera. The detection module can analyze the image data provided by the at least one camera to detect the lane change initiated by the driver. For example, lane markings can be detected in the image data, wherein a horizontal change in the position of the lane markings in the image can be used to conclude that a lane change has occurred or been initiated.
[0015] However, the present disclosure is not limited to cameras, and detection data from at least one infrared sensor and / or a lidar system can be used additionally or alternatively to detect the driver-initiated lane change. For example, at least one infrared sensor can be provided on an underbody of the vehicle to detect whether the vehicle crosses a lane marking. From this, it can be concluded that a lane change has occurred or been initiated.
[0016] Optionally, the detection module can use additional information in addition to the detection data to detect the driver-initiated lane change, such as a steering angle, digital map data, a vehicle position, etc.
[0017] Preferably, the gaze behavior includes the driver's gaze direction, in particular toward one side of the vehicle. The gaze direction can, for example, provide information about whether the driver is looking toward an adjacent lane to which the detected lane change leads and / or a side mirror. If this is the case, it can be concluded that the detected lane change is an intentional lane change. However, if the driver does not look toward the adjacent lane to which the detected lane change leads and / or the side mirror, it can be concluded that the detected lane change is an unintentional lane change.
[0018] Typically, the driver assistance system can be configured to detect the direction of gaze using eye tracking. The term "eye tracking" refers in particular to the recording of eye movements, which are detected, for example, by a camera in the interior sensor system. This allows insights into where a person is looking. The gaze behavior preferably includes a glance over the shoulder. The glance over the shoulder can, for example, provide information about whether the driver is looking towards an adjacent lane to which the detected lane change leads. If this is the case, it can be concluded that the detected lane change is an intentional lane change. However, if the driver does not perform a glance over the shoulder, it can be concluded that the detected lane change is an unintentional lane change.
[0019] Preferably, the analysis module is configured to derive the gaze behavior from a (spatial) head orientation. The terms "orientation" and "spatial orientation," as used in the present disclosure, refer to an arrangement or pose of the driver's head in three-dimensional space, from which, for example, a gaze direction and / or a shoulder glance can be derived. The orientation can include one-dimensional, two-dimensional, or three-dimensional information relating to the arrangement or pose of the driver's head. The orientation can be absolute or relative.
[0020] Preferably, the analysis module is configured to derive gaze behavior from a head position. The term “position,” as used in the present disclosure, refers to a location of the driver’s head. The position may be absolute or relative, in particular relative to the vehicle. In some embodiments, the driver’s head may be specified by a reference point (e.g., estimated center point or estimated center of gravity) to which coordinates in three-dimensional space (x, y, z) are assigned. These coordinates may specify the position or location of the driver’s head. The position or location of the driver’s head may, for example, provide an indication of a shoulder glance.
[0021] The interior sensor system preferably comprises at least one interior camera. The at least one interior camera can output image data as the detection data. The image data is preferably video data. The term "video data" refers to the recording and processing of moving images. Optionally, the interior sensor system can comprise at least one light source. In some embodiments, the light source can be an infrared light source, and the at least one interior camera can be at least one infrared camera.
[0022] Additionally or alternatively, the interior sensor system comprises at least one interior radar. The at least one interior radar can output radar data as the detection data.
[0023] The analysis module can analyze the detection data from the interior sensors using suitable software, such as an object recognition algorithm, to detect the driver's gaze behavior (e.g., the direction of gaze using eye tracking and / or the position and / or orientation of the driver's head) in the detection data. The object recognition algorithm can be trained, for example, using deep learning to precisely determine the gaze behavior.
[0024] Preferably, the analysis module is configured to categorize the detected lane change as an intentional lane change if the gaze behavior indicates that the driver is looking at a side mirror in a lane change direction and / or is performing a shoulder check in the lane change direction; and to categorize the detected lane change as an unintentional lane change if the gaze behavior indicates that the driver is not looking at the side mirror in the lane change direction and / or is not performing a shoulder check in the lane change direction.
[0025] Preferably, the analysis module is configured to categorize the detected lane change based on a steering torque. For example, a temporal change and / or the strength of the steering torque applied by the driver can provide an indication of whether the initiated lane change is intentional or unintentional.
[0026] Additionally or alternatively, the analysis module is configured to categorize the detected lane change based on a steering angle. For example, a change over time and / or the strength of the left angle set by the driver can provide an indication as to whether the initiated lane change is intentional or unintentional. The steering angle can correspond to a steering wheel position and thus a position of the front wheels in relation to a longitudinal axis of the vehicle. Additionally or alternatively, the analysis module is configured to categorize the detected lane change based on a pedal position, in particular an accelerator pedal position and / or a brake pedal position. For example, a sudden and strong application of the brake pedal can provide an indication that the lane change is intentional. However, if the accelerator pedal position is unchanged orconstant, this may be an indication that the lane change was unintentional.
[0027] Additionally or alternatively, the analysis module is configured to categorize the detected lane change based on lane information. For example, the vehicle's environmental sensors may detect that there is a hard shoulder next to the ego lane, which could indicate that the initiated lane change was unintentional.
[0028] Additionally or alternatively, the analysis module is configured to categorize the detected lane change based on (digital) map information. For example, the map information may indicate that there is a hard shoulder next to the driver's lane, which could be an indication that the initiated lane change was unintentional.
[0029] Additionally or alternatively, the analysis module is configured to categorize the detected lane change based on information about the navigation route. For example, the navigation route may require leaving a multi-lane road. Lane changes are therefore necessary to follow the navigation route. This may be an indication that the initiated lane change is intentional.
[0030] Additionally or alternatively, the analysis module is configured to categorize the detected lane change based on the road's curvature radius. For example, by comparing the road's curvature radius with the steering angle and / or steering torque, it can be determined whether an intentional or unintentional lane change has occurred. For example, if a higher steering angle and / or higher steering torque than necessary for lane guidance is identified, an intentional lane change can be detected by taking the driver's gaze behavior into account.
[0031] Additionally or alternatively, the analysis module is configured to categorize the detected lane change based on driver attention. For example, the driver can be monitored using interior sensors, such as an interior camera and / or an interior microphone. If an analysis of the monitoring data reveals that the driver is inattentive, this may be an indication that the initiated lane change was unintentional. If, on the other hand, the analysis of the monitoring data reveals that the driver is attentive, this may be an indication that the initiated lane change was intentional.
[0032] Additionally or alternatively, the analysis module is configured to categorize the detected lane change based on environmental information, particularly with respect to at least one other road user. For example, if it is detected that another vehicle is in the adjacent lane at the same level or emits light signals and / or acoustic signals (e.g., horn), this may indicate that the initiated lane change was unintentional.
[0033] Preferably, the at least one control module is configured to control the at least one vehicle function such that an acoustic and / or optical and / or haptic warning is issued to the driver if the detected lane change is categorized as an unintentional lane change by the analysis module. The warning is a signal to the driver that the ego lane is being left. The acoustic warning can be issued to the driver, for example, via at least one interior loudspeaker. The optical warning can be issued to the driver, for example, via at least one display device, such as a central information output device of an infotainment system (e.g., head unit or pillar-to-pillar display). The haptic warning can be issued to the driver, for example, by a vibration of the steering wheel.Preferably, the at least one control module is configured to control the at least one vehicle function such that a steering system of the vehicle actively intervenes if the detected lane change is categorized by the analysis module as an unintentional lane change, in order to prevent the vehicle from leaving a current lane and return it to the current lane. In particular, counter-steering can be initiated to prevent the vehicle from leaving the ego lane.
[0034] Preferably, the at least one control module is configured to control the at least one vehicle function in such a way that the lane change is enabled without countermeasures by the driver assistance system if the detected lane change is categorized as an intentional lane change by the analysis module. For example, no active countersteering can be performed by the steering system if the detected lane change is categorized as an intentional lane change by the analysis module.
[0035] Preferably, the at least one control module is configured to control the at least one vehicle function such that the lane change is actively and / or passively supported by the driver assistance system if the detected lane change is categorized as an intentional lane change by the analysis module. Active support can, for example, be co-steering by the steering system, so that the vehicle changes from the first lane to the adjacent lane with an optimal trajectory. Passive support can, for example, be the omission of measures that hinder the lane change, such as counter-steering by the steering system.
[0036] Preferably, the at least one control module is configured to control the at least one vehicle function such that a turn signal is activated if the detected lane change is categorized by the analysis module as an intended lane change. This allows the lane change to be signaled externally, thereby improving road safety.
[0037] Preferably, the driver assistance system is configured to categorize the detected lane change and trigger the at least one vehicle function only if the lane change is detected while a turn signal is deactivated. If the turn signal is activated by the driver when the lane change is detected, it can be concluded that the lane change is intentional, and further analysis of the driver's gaze behavior can be omitted.
[0038] According to a further independent aspect of the present disclosure, a vehicle, in particular a motor vehicle, is specified. The vehicle comprises the driver assistance system according to the embodiments of the present disclosure.
[0039] The term "vehicle" includes cars, trucks, buses, mobile homes, motorcycles, etc., used to transport people, goods, etc. In particular, the term includes motor vehicles used to transport people.
[0040] In some embodiments, the driver assistance system may be a lane-keeping assistant, such as a passive lane-keeping assistant or an active lane-keeping assistant. The passive lane-keeping assistant warns the driver when the vehicle leaves the ego lane. The active lane-keeping assistant can actively intervene in the steering to keep the vehicle in the ego lane. In other words, the driver assistance system can provide assistive and / or partially automated and / or automated lateral guidance.
[0041] According to a further independent aspect of the present disclosure, a driver assistance method for a vehicle, in particular a motor vehicle, is specified. The driver assistance method comprises detecting, by the vehicle, a lane change initiated by a driver; detecting the driver using an interior sensor system and outputting corresponding detection data; determining the driver's gaze behavior based on the detection data from the interior sensor system; categorizing, by the vehicle, the detected lane change as an intended lane change or an unintentional lane change based on the driver's gaze behavior; and controlling at least one vehicle function based on the categorization of the lane change. The driver assistance method can implement the aspects of the driver assistance system described in this document.
[0042] According to a further independent aspect of the present disclosure, a software (SW) program is provided. The SW program can be configured to be executed on one or more processors and thereby to carry out the driver assistance method described in this document.
[0043] According to a further independent aspect of the present disclosure, a storage medium is provided. The storage medium may comprise a software program configured to be executed on one or more processors and thereby to execute the driver assistance method described in this document.
[0044] According to a further independent aspect of the present disclosure, software with program code is provided. The software is configured to implement the driver assistance method when the software runs on one or more software-controlled devices.
[0045] According to a further independent aspect of the present disclosure, a driver assistance system for a vehicle is provided. The driver assistance system comprises one or more processors; and at least one memory connected to the one or more processors and containing instructions executable by the one or more processors to carry out the driver assistance method described in this document.
[0046] A processor or processor module is a programmable computing unit, i.e. a machine or an electronic circuit that controls other elements according to given instructions and thereby drives an algorithm (process).
[0047] Brief Description of the Drawings Embodiments of the disclosure are illustrated in the figures and are described in more detail below. They show:
[0048] Figure 1 schematically shows a vehicle with a driver assistance system according to embodiments of the present disclosure,
[0049] Figure 2 schematically shows a vehicle performing a lane change according to embodiments of the present disclosure,
[0050] Figure 3 schematically shows a vehicle and a driver's gaze behavior according to embodiments of the present disclosure,
[0051] Figure 4 is a flowchart of a driver assistance method for a vehicle according to embodiments of the present disclosure.
[0052] Embodiments of the disclosure
[0053] In the following, unless otherwise stated, the same reference symbols are used for identical and equivalent elements.
[0054] Figure 1 schematically shows a vehicle 10 with driver assistance system 100 according to embodiments of the present disclosure. Figure 2 schematically shows the vehicle 10 performing a lane change SW. Figure 3 schematically shows the vehicle 10 and a gaze behavior B1, B2, B3 of the driver F.
[0055] The driver assistance system 100 comprises a detection module 110 configured to detect a lane change SW initiated by the driver F; an interior sensor system 120 configured to detect the driver F (e.g., a head K of the driver F) and output corresponding detection data; an analysis module 130 configured to determine a gaze behavior B1, B2, B3 of the driver F based on the detection data and to categorize the detected lane change SW into an intended (or conscious) lane change or an unintentional (or unconscious) lane change based on the gaze behavior B1, B2, B3; and at least one control module 140 configured to control at least one vehicle function based on the categorization of the detected lane change SW.
[0056] In some embodiments, the driver assistance system 100 may be a lane-keeping assistant, such as a passive lane-keeping assistant or an active lane-keeping assistant. The passive lane-keeping assistant warns the driver F when the vehicle 10 leaves the ego lane. The active lane-keeping assistant can perform active steering interventions to keep the vehicle 10 in the ego lane. In other words, at least automated lateral guidance can be provided by the driver assistance system 100.
[0057] The recognition module 110 preferably uses detection data from at least one sensor module to detect the lane change SW initiated by the driver F. The at least one sensor module can, for example, comprise at least one camera, in particular at least one exterior camera. The recognition module 110 can analyze the image data provided by the at least one camera to detect the lane change SW initiated by the driver F. For example, lane markings can be detected in the image data, wherein a horizontal change in the position of the lane markings in the image can be used to conclude that a lane change has occurred or been initiated. Optionally, the recognition module 110 can use further information in addition to the detection data to detect the lane change SW initiated by the driver F, such as a steering angle, digital map data, a vehicle position, etc.
[0058] The analysis module 120 uses the gaze behavior B1, B2, B3 of the driver F to categorize the detected lane change SW. In particular, the analysis module 120 detects whether it is an intentional lane change or an unintentional lane change. For this purpose, the analysis module 120 can use, in addition to the gaze behavior B1, B2, B3, a variety of suitable input data, such as a steering torque, a steering angle, a pedal position (e.g., an accelerator pedal position and / or brake pedal position), lane information, map information, a road curvature radius, driver attention, and / or environmental information (e.g., with respect to at least one other road user).
[0059] In some embodiments, the analysis module 130 can be configured to categorize the detected lane change SW based on a roadway curvature radius. In particular, by comparing the roadway curvature radius with a steering angle and / or steering torque, it can be determined whether an intentional lane change or an unintentional lane change has occurred. The intention to leave the lane or change lanes can be detected, in particular, based on a lower or higher steering angle and / or steering torque relative to a route.
[0060] Preferably, the gaze behavior B1, B2, B3 includes a gaze direction of the driver F, such as a gaze direction B1 straight ahead and / or a gaze direction B2 to the side of the vehicle 10. The gaze direction B2 to the side of the vehicle 10 can, for example, provide information about whether the driver F is looking towards an adjacent lane to which the detected lane change SW leads and / or a side mirror. If this is the case, it can be concluded that the detected lane change SW is an intentional lane change. However, if the driver F is looking straight ahead (gaze direction B1), it can be concluded that the detected lane change SW is an unintentional lane change.
[0061] Typically, the driver assistance system 100 can be configured to detect the direction of gaze B1, B2 using eye tracking. The term "eye tracking" refers in particular to the detection of eye movements, which are detected, for example, by a camera of the interior sensor system 120. This allows insights into where the driver F is looking.
[0062] The gaze behavior Bl, B2, B3 preferably includes a shoulder glance B3. The shoulder glance B3 can, for example, provide information about whether the driver F is looking towards an adjacent lane to which the detected lane change SW leads. If this is the case, it can be concluded that the detected lane change SW is an intentional lane change. However, if the driver F does not perform a shoulder glance B3, it can be concluded that the detected lane change SW is an unintentional lane change. The gaze direction Bl straight ahead or in the direction of travel can, for example, be recognized if the recognized gaze direction and / or a head orientation lies in a first angular range. Similarly, the gaze direction B2 to the side (e.g. towards a side mirror) can be recognized if the recognized gaze direction and / or a head orientation lies in a second angular range that differs from the first angular range.In addition, the shoulder glance B3 can be detected if the detected gaze direction and / or a head orientation lies in a third angular range that differs from the first angular range and the second angular range.
[0063] Preferably, the analysis module 130 is configured to derive the gaze behavior B1, B2, B3 from a (spatial) head orientation. The terms "orientation" and "spatial orientation," as used in the present disclosure, refer to an arrangement or pose of the head K of the driver F in three-dimensional space, from which, for example, a gaze direction B1, B2 and / or a shoulder glance B3 can be derived. The orientation can comprise one-dimensional, two-dimensional, or three-dimensional information relating to the arrangement or pose of the head K of the driver F.
[0064] Preferably, the analysis module 130 is configured to derive the gaze behavior B1, B2, B3 from a head position. The term “position,” as used in the present disclosure, refers to a location of the head K of the driver F. The position can be absolute or relative, in particular relative to the vehicle 10. In some embodiments, the head K of the driver F can be specified by a reference point (e.g., estimated center point or estimated center of gravity) to which coordinates in three-dimensional space (x, y, z) are assigned. These coordinates can specify the position or location of the head K of the driver F. The position or location of the head K of the driver F can, for example, provide an indication of a shoulder glance B3.
[0065] The at least one control module 140 controls the at least one vehicle function based on the categorization of the lane change SW. For example, an acoustic and / or optical and / or haptic warning can be issued to the driver F and / or a steering system of the vehicle 10 can actively intervene in the vehicle guidance if the detected lane change is categorized by the analysis module 130 as an unintentional lane change. In a further example, the lane change SW can be actively and / or passively assisted by the driver assistance system 100 if the detected lane change SW is categorized by the analysis module 130 as an intentional lane change. Active assistance can, for example, be steering assistance by the steering system, so that the vehicle 10 changes from the first lane to the adjacent lane with an optimal trajectory.Passive assistance can, for example, be the omission of measures that hinder the lane change SW, such as counter-steering by the steering system.
[0066] In some embodiments, the at least one control module 140 can be configured to control the at least one vehicle function such that a turn signal is activated if the detected lane change SW is categorized as an intended lane change by the analysis module 130. This allows the lane change SW to be signaled externally, thereby improving road safety.
[0067] Figure 4 schematically shows a flowchart of a driver assistance method 400 for a vehicle according to embodiments of the present disclosure. The driver assistance method 400 can be implemented by appropriate software executable by one or more processors (e.g., a CPU).
[0068] The driver assistance method 400 comprises, in block 410, the vehicle detecting a lane change initiated by a driver; in block 420, the driver is detected by an interior sensor system and corresponding detection data is output; in block 430, the driver's gaze behavior is determined based on the detection data from the interior sensor system; in block 440, the vehicle categorizes the detected lane change as an intended lane change or an unintentional lane change based on the driver's gaze behavior; and in block 450, the driver activates at least one vehicle function based on the categorization of the lane change. According to the invention, the driver's gaze behavior is used to distinguish between an intended or deliberate lane change and an unintentional or unconscious lane change.The driver assistance system controls at least one vehicle function, such as a lane keeping assistance function, based on the discrimination, so that, for example, annoying warnings and / or steering interventions for the driver can be avoided. As a result, the reliability of the driver assistance system can be improved and road safety increased, as the driver is not tempted to deactivate the system due to unwanted interventions.
[0069] Although the invention has been illustrated and explained in detail by means of preferred embodiments, the invention is not limited by the disclosed examples, and other variations may be derived therefrom by those skilled in the art without departing from the scope of the invention. It is therefore clear that a multitude of possible variations exist. It is also clear that the embodiments mentioned by way of example are truly only examples and should not be construed as limiting the scope, possible applications, or configuration of the invention in any way.Rather, the preceding description and the description of the figures enable the person skilled in the art to implement the exemplary embodiments in concrete terms, whereby the person skilled in the art, with knowledge of the disclosed inventive concept, can make various changes, for example with regard to the function or the arrangement of individual elements mentioned in an exemplary embodiment, without departing from the scope of protection defined by the claims and their legal equivalents, such as further explanations in the description.
Claims
Patent claims 1. A driver assistance system (100) for a vehicle (10), comprising: a detection module (110) configured to detect a lane change (SW) initiated by a driver (F); an interior sensor system (120) configured to detect the driver (F) and output corresponding detection data; an analysis module (130) configured to determine a gaze behavior (B1, B2, B3) of the driver (F) based on the detection data, and to categorize the detected lane change (SW) into an intended lane change or an unintentional lane change based on the gaze behavior (B1, B2, B3); and at least one control module (140) configured to control at least one vehicle function based on the categorization of the detected lane change (SW).
2. The driver assistance system (100) according to claim 1, wherein: the gaze behavior (Bl, B2, B3) comprises a gaze direction (Bl, B2), in particular toward a side mirror of the vehicle (10); and / or the gaze behavior (Bl, B2, B3) comprises a shoulder glance (B3); and / or the analysis module (130) is configured to derive the gaze behavior (Bl, B2, B3) from a head orientation; and / or the analysis module (130) is configured to derive the gaze behavior (Bl, B2, B3) from a head position.
3. Driver assistance system (100) according to claim 1 or 2, wherein the analysis module (130) is configured to: categorize the detected lane change (SW) as an intended lane change if the gaze behavior (Bl, B2, B3) indicates that the driver (F) is looking at a side mirror in a lane change direction and / or is performing a shoulder check (B3) in the lane change direction; and categorize the detected lane change (SW) as an unintentional lane change if the gaze behavior (Bl, B2, B3) indicates that the driver (F) is does not look at the side mirror in the direction of the lane change and / or does not check his shoulder (B3) in the direction of the lane change.
4. Driver assistance system (100) according to one of claims 1 to 3, wherein the analysis module (130) is configured to further categorize the detected lane change (SW) based on at least one of the following aspects: a steering torque; a steering angle; a pedal position, in particular an accelerator pedal position and / or a brake pedal position; track information; map information; Information about the navigation route; a road curvature radius, particularly in combination with the steering angle; driver attention; Environmental information, in particular with regard to at least one other road user.
5. Driver assistance system (100) according to one of claims 1 to 4, wherein the interior sensor system (120) comprises: at least one interior camera; and / or at least one interior radar.
6. Driver assistance system (100) according to one of claims 1 to 5, wherein the at least one control module (140) is configured to control the at least one vehicle function in such a way that: an acoustic and / or optical and / or haptic warning is issued to the driver (F) if the detected lane change (SW) is categorized by the analysis module (130) as an unintentional lane change; and / or a steering system of the vehicle (10) actively intervenes if the detected lane change (SW) is categorized by the analysis module (130) as an unintentional lane change, in order to to prevent a departure from a current lane and to return the vehicle (10) to the current lane; and / or the lane change (SW) is enabled without countermeasures by the driver assistance system (100) if the detected lane change (SW) is categorized as an intended lane change by the analysis module (130); and / or the lane change (SW) is actively and / or passively supported by the driver assistance system (100) if the detected lane change (SW) is categorized as an intended lane change by the analysis module (130); and / or a direction indicator is activated if the detected lane change (SW) is categorized as an intended lane change by the analysis module (130).
7. Driver assistance system (100) according to one of claims 1 to 6, wherein the driver assistance system (100) is configured to carry out the categorization of the detected lane change (SW) and the activation of the at least one vehicle function only if the lane change (SW) is detected while a direction indicator is deactivated.
8. Vehicle (10), in particular a motor vehicle, comprising the driver assistance system (100) according to one of claims 1 to 7.
9. Driver assistance method (400) for a vehicle, comprising: Detecting (410), by the vehicle, a lane change initiated by a driver; Detecting (420) the driver by an interior sensor system and outputting corresponding detection data; Determining (430) a gaze behavior of the driver based on the detection data of the interior sensor system; Performing (440), by the vehicle, a categorization of the detected lane change into an intended lane change or an unintentional lane change based on the driver's gaze behavior; and Controlling (450) at least one vehicle function based on the categorization of the lane change.
10. A storage medium comprising a software program configured to be executed on one or more processors and thereby to execute the driver assistance method (400) according to claim 9.
Citation Information
Patent Citations
Driver intention-based lane assistant system for autonomous driving vehicles
US20190071091A1
Lane departure warning determination method using driver state monitoring
US20210001875A1
Vehicle controller and method thereof
US20220161805A1
