Method for operating a driving function of a vehicle

Abstract

Method (200, 210) for operating a driving function of a vehicle (100); wherein the driving function is configured to carry out an at least partially automated lateral guidance of the vehicle (100) and / or to assist a driver of the vehicle (100) in the lateral guidance of the vehicle (100); wherein the method (200, 210) comprises - Determining (201) environmental data relating to visibility conditions on a roadway (110) located in front of the vehicle (100) in the direction of travel; wherein the environmental data indicate a specific visibility situation from a plurality of predefined, different visibility situations; wherein the different situations differ with respect to a density of fog and / or an amount of precipitation; - Operating (202) at least one lighting unit (102) of the vehicle (100), which is configured to emit light (106) onto the roadway (110) located in front of the vehicle (100) in the direction of travel, as a function of the determined specific visibility situation and as a function of lighting characteristics; wherein the lighting characteristics indicate different properties of the light (106) to be emitted by the lighting unit (102) for the different visibility situations; - capturing (203) image data relating to the roadway (110) in front of the vehicle (100) in the direction of travel; - detecting at least one lane marking (111) based on the acquired image data; and - Operating (204) the driving function depending on the detected lane marking (111).

Description

[0001] The invention relates to a method and a corresponding control unit for operating a driving function, in particular a lateral guidance assistant, of a vehicle.

[0002] A vehicle, particularly a road vehicle, may have a lateral guidance assistant that assists the driver in lateral guidance of the vehicle. Examples of lateral guidance assistants include a lane keeping assistant, which helps the driver maintain a lane, or a lane change assistant, which assists the driver in changing lanes.

[0003] To provide a lateral guidance assistant, a vehicle typically has one or more environmental sensors, in particular cameras or image sensors, which are configured to capture sensor data, in particular image data, relating to lane markings of the roadway traveled by the vehicle. The availability and / or reliability of a lateral guidance assistant typically depend on the quality with which the lane markings can be captured by the image data from the one or more image sensors.

[0004] DE 10 2016 009 507 A1 describes a method for detecting light signals. DE 10 2016 014 708 A1 describes a method for controlling the front light distribution of a vehicle. US 2014 / 0 071 702 A1 describes a method for influencing a lighting situation in front of a vehicle. DE 10 2014 009 421 A1 describes a method for operating a camera of a motor vehicle. DE 10 2008 001 551 A1 describes a method for automatically adjusting the luminance of a lighting device of a vehicle. US 2018 / 0 186 278 A1 describes a method for illuminating the front of a vehicle. DE 10 2015 009 875 A1 describes a method for autonomous driving of a vehicle. DE 10 2017 207 932 A1 describes a method for operating a lighting system of a motor vehicle. DE 10 2018 111 265 A1 describes a vision system of a vehicle.

[0005] This document deals with the technical task of efficiently increasing the availability and / or reliability of a driving function, in particular a lateral guidance assistant.

[0006] The problem is solved by each of the independent claims. Advantageous embodiments are described, among other things, in the dependent claims. It should be noted that additional features of a patent claim dependent on an independent patent claim can form a separate invention, independent of the combination of all features of the independent patent claim, without the features of the independent patent claim or only in combination with a subset of the features of the independent patent claim, which invention can be made the subject of an independent claim, a divisional application, or a subsequent application. This applies equally to technical teachings described in the description, which can form an invention independent of the features of the independent patent claims.

[0007] According to one aspect, a method for operating or for operating a driving function of a vehicle is described. The driving function can be configured to carry out at least partially automated longitudinal and / or lateral guidance of the vehicle and / or to assist a driver of the vehicle in the longitudinal and / or lateral guidance of the vehicle. The driving function can, for example, comprise a lateral guidance assistant or be a lateral guidance assistant. In particular, the driving function can be configured to assist the driver of the vehicle when changing lanes. Alternatively or additionally, the driving function can be configured to assist the driver of the vehicle in maintaining a lane or remaining within a lane of a roadway. Alternatively or additionally, the driving function can be configured to assist the driver of the vehicle when driving at a speed (prescribed by a traffic sign).

[0008] The method comprises determining environmental data relating to visibility conditions on a roadway in front of the vehicle in the direction of travel and / or on a traffic sign arranged in front of the vehicle in the direction of travel. The environmental data can indicate or identify a specific situation from a plurality of predefined situations. The different situations can differ, for example, in relation to: the density of fog, the amount of precipitation and / or the brightness. The different visibility conditions can be defined in relation to an image sensor that is used to capture image data for the driving function. In particular, different visibility situations can be defined which, when using a specific image sensor, lead to image data with (significantly) different properties.lead to image data that differ significantly in terms of the reliability and / or quality with which road markings can be detected on the basis of the image data.

[0009] The method also includes operating at least one lighting unit of the vehicle depending on the ambient data or depending on the determined visibility situation. The lighting unit can be configured to emit light onto the roadway in front of the vehicle in the direction of travel and / or onto the traffic sign located in front of the vehicle in the direction of travel. A vehicle can comprise multiple lighting units to emit light onto the roadway and / or onto a traffic sign. A lighting unit can comprise, for example, a headlight and / or a high beam and / or a fog light.

[0010] The roadway lighting can thus be adjusted depending on the current visibility conditions. This can improve the quality of the image data captured by an image sensor. In particular, the roadway and / or traffic sign lighting can be adjusted in such a way that the effects of the current visibility conditions on the reliability and / or quality of the recognition of road markings and / or traffic signs based on the image data are at least partially or as completely as possible compensated.

[0011] The one or more lighting units of the vehicle can (also) be operated depending on lighting characteristics. The lighting characteristics can indicate different properties of the light emitted by the one or more lighting units for different values ​​of the ambient data or for different visibility situations. In other words, the lighting characteristics can indicate how the light emitted by the one or more lighting units is to be adapted to the respective prevailing visibility situation. In still other words, the lighting characteristics can indicate, for a specific visibility situation, the properties of the light emitted by the one or more lighting units, by means of which the quality of the image data captured by an image sensor (e.g. for the recognition of road markings and / or traffic signs) is increased, at least on a statistical average.

[0012] The lighting characteristics can, for example, have been determined experimentally in advance. Furthermore, the lighting characteristics can be stored on a memory unit of the vehicle. Thus, the lighting characteristics can indicate empirical values ​​regarding which form of illumination of the roadway and / or traffic sign (i.e., which one or more properties of the light) can increase, in particular maximize, the quality of the captured image data of the roadway and / or traffic sign (given a specific visibility situation).

[0013] The method also includes capturing image data relating to the roadway in front of the vehicle in the direction of travel and / or to the traffic sign located in front of the vehicle in the direction of travel. The image data can be captured using one or more image sensors or cameras of the vehicle. For example, the image data can include an image of the roadway and / or the traffic sign at a specific point in time. Furthermore, the image data can include a corresponding (temporal) sequence of images of the roadway and / or the traffic sign at a sequence of points in time. An image can have a matrix of N x M pixels (e.g., with N and / or M equal to 100, 500, 1000 or more).By illuminating the roadway and / or traffic sign with one or more lighting units, with the illumination being adapted to the prevailing visibility conditions, the quality of the captured image data can be improved (compared to illuminating the roadway and / or traffic sign that is not adapted to the prevailing visibility conditions). In particular, the quality of the image data can be improved with respect to its use in the context of the driving function (e.g., with respect to the recognition of road markings and / or speed limits).

[0014] The method further comprises operating the driving function based on the acquired image data. In particular, at least one lane marking on the road can be detected based on the image data. The driving function can then be operated depending on the detected lane marking. Due to the optimized illumination of the road and the resulting quality of the image data, the reliability and / or availability of the driving function can also be increased.

[0015] The illumination characteristics can depend on one or more properties of the one or more environmental sensors, in particular image sensors, used to capture the image data. In other words, the illumination characteristics can be tailored to the type and / or properties of the image sensor. For example, different illumination characteristics can be provided for different types of image sensors and / or different properties of an image sensor. The one or more properties of the image sensor can include: the sensitivity of the image sensor, the dynamic range of the image sensor, the pixel resolution of the image sensor, and / or the pixel size of pixels of the image sensor. By using illumination characteristics that depend on the one or more image sensors used to capture the image data, the quality of the captured image data can be further increased with regard to the use of the image data within the context of the driving function.

[0016] Alternatively or additionally, the lighting characteristics can depend on an image processing algorithm used to evaluate the image data, in particular to detect lane markings and / or speed limits, within the scope of the driving function. In particular, the lighting characteristics can indicate, for different visibility situations, one or more properties of the light to be emitted, by which the reliability and / or quality of the image processing algorithm used within the scope of the driving function is improved, in particular maximized (on average). By using lighting characteristics that depend on the image processing algorithm used, the reliability and / or availability of a driving function can be further increased.

[0017] The one or more properties of the light emitted by a lighting unit may include: a spatial distribution of the light on the roadway and / or the traffic sign; and / or an intensity of the light, in particular a spatial distribution of the intensity of the light on the roadway and / or the traffic sign; and / or a spectral composition of the light; and / or a direction and / or orientation of a luminous cone of the light.

[0018] The environmental data used to determine the current visibility situation can include or be based on: sensor data from a vehicle's light sensor; and / or sensor data from a vehicle's rain sensor; and / or sensor data from an image camera or image sensor of the vehicle; and / or data from a Car-to-X message received by the vehicle. This allows the current visibility situation to be determined precisely.

[0019] According to a further aspect, a further method for operating or operating a driving function of a vehicle is described. The aspects described in this document are also applicable to this method.

[0020] The method comprises capturing image data relating to the roadway in front of the vehicle in the direction of travel and / or the traffic sign located in front of the vehicle in the direction of travel. The image data can be captured using one or more environmental sensors, in particular one or more image sensors. The image data can display an image of the roadway and / or the traffic sign for a specific point in time.

[0021] The method also includes determining quality data relating to the quality of the acquired image data for use in the driving function. In particular, the quality data can indicate the quality and / or reliability with which a lane marking and / or the type of traffic sign can be detected based on the acquired image data. To determine the quality data, for example, a signal-to-noise ratio of the image data can be determined. A relatively low signal-to-noise ratio indicates a relatively low quality (and vice versa). Alternatively or additionally, an image processing algorithm can be applied to the image data to determine the quality data, e.g., to detect a lane marking and / or the type of traffic sign. The reliability and / or quality with which the image processing algorithm can be applied to the image data can then be determined as quality data (e.g.,to recognize a lane marking and / or the type of traffic sign).

[0022] The method also includes operating at least one lighting unit of the vehicle such that the quality of the captured image data, indicated by the quality data, is increased for use within the driving function. As explained above, a lighting unit is configured to emit light (with one or more adjustable properties) onto the roadway in front of the vehicle in the direction of travel and / or onto the traffic sign in front of the vehicle in the direction of travel. In particular, the lighting unit can be operated such that one or more properties of the emitted light are adjusted such that the quality of the captured image data, indicated by the quality data, is increased for use within the driving function.

[0023] In other words, the one or more properties of the light emitted by a lighting unit of the vehicle for illuminating the roadway and / or the traffic sign can be adapted, in particular optimized, to ensure that the image data of the roadway and / or the traffic sign captured by an image sensor enable reliable and / or precise operation of the driving function.

[0024] The adjustment of one or more properties of the light can be carried out as part of an iterative process. In particular, the steps of acquiring image data, determining quality data and adjusting one or more properties of the light can be repeated (e.g. at a sequence of points in time) in order to iteratively increase the quality of the acquired image data indicated by the quality data for use in the driving function. In this way, the lighting situation of the roadway and / or the traffic sign can be gradually adapted to the current visibility conditions in order to be able to acquire image data with a high quality. Furthermore, the one or more properties of the light emitted by a lighting unit can be automatically adapted to changing visibility conditions.

[0025] Alternatively or additionally, the method may include determining, based on the image data, the visibility conditions on the roadway ahead of the vehicle in the direction of travel and / or on the traffic sign ahead of the vehicle in the direction of travel. For example, one situation can be selected from a plurality of different, predefined situations based on the image data (as already explained above).

[0026] The lighting unit can then also be operated depending on lighting characteristics, whereby the lighting characteristics indicate different properties of the light emitted by the lighting unit for different visibility situations. In particular, the specific properties of the light to be emitted can be determined based on the lighting characteristics. These light properties can then, if necessary, be used as a starting point for further iterative optimization or improvement of the light properties. By taking into account (preliminarily determined) lighting characteristics, the convergence of setting the optimized light properties for illuminating the roadway and / or traffic sign can be accelerated.

[0027] The method further comprises operating the driving function based on the acquired image data. In particular, one or more lane markings and / or the type of traffic sign can be detected for operating the driving function based on the image data acquired (under optimized lighting conditions).

[0028] Within the framework of the methods described in this document, one or more properties of the light emitted by the one or more lighting units of a vehicle can be adjusted to increase the reliability and / or quality of the recognition of lane markings and / or the type of traffic sign. In particular, the spatial intensity distribution of the emitted light can be adjusted such that the proportion of the emitted light that hits the one or more lane markings of the traveling roadway and / or a traffic sign is increased.

[0029] In particular, for this purpose, a road marking and / or a traffic sign can be detected based on the image data acquired at a first point in time. The intensity distribution and / or the light cone of the light emitted by the one or more lighting units can then be changed depending on the detected road marking, in particular by increasing the proportion of light that hits the road marking and / or the traffic sign. Image data relating to the road and / or the traffic sign can then be acquired at a subsequent second point in time with the adjusted intensity distribution and / or with the differently aligned light cone.

[0030] For example, the lighting unit can be operated in such a way that the intensity distribution of the light is adjusted depending on the quality data (e.g. repeatedly at a sequence of times).

[0031] Alternatively or additionally, the method may include detecting a local area within the acquired image data in which a lane marking and / or a traffic sign is displayed. The lighting unit can then be operated such that the intensity of the emitted light is increased in the area of ​​the lane and / or traffic sign indicated by the acquired image data.

[0032] The acquisition of image data and the adjustment of the light intensity distribution can be repeated iteratively for a sequence of time points. This ensures that lane markings and / or traffic signs can be detected with high reliability.

[0033] A method described in this document can comprise predicting the course of the roadway ahead of the vehicle in the direction of travel. For this purpose, for example, the current position of the vehicle can be determined (e.g. based on the vehicle's GPS coordinates). Furthermore, digital map information can be used to predict the course of the roadway currently being traveled on. Alternatively or additionally, the current course of the roadway can be used to infer the course of the roadway ahead. The at least one lighting unit of the vehicle can then (also) be operated depending on the predicted course of the roadway. In this way, the quality of the recorded image data with regard to the roadway and / or with regard to traffic signs along the roadway can be further increased.

[0034] According to a further aspect, a control unit is described which is configured to carry out at least one of the methods described in this document.

[0035] According to a further aspect, a road vehicle (in particular a passenger car or a truck or a bus or a motorcycle) is described which comprises the control unit described in this document.

[0036] According to another aspect, a software (SW) program is described. The SW program can be configured to be executed on a processor and thereby to perform at least one of the methods described in this document.

[0037] According to a further aspect, a storage medium is described. The storage medium can comprise a software program configured to be executed on a processor and thereby to carry out at least one method described in this document.

[0038] It should be noted that the methods, devices, and systems described in this document can be used both alone and in combination with other methods, devices, and systems described in this document. Furthermore, any aspects of the methods, devices, and systems described in this document can be combined in a variety of ways. In particular, the features of the claims can be combined in a variety of ways.

[0039] The invention will be described in more detail below using exemplary embodiments. Fig. 1 an exemplary vehicle traveling on a roadway with a lane marking; and Fig. 2a and Fig. 2b Flow diagrams of exemplary methods for operating a driving function of a vehicle.

[0040] As stated at the beginning, this document deals with increasing the availability and / or reliability of a vehicle's driving function, in particular a lateral guidance assistant. The following section specifically addresses the detection of lane markings. It should be noted that the aspects described apply accordingly to the detection of (types of) traffic signs.

[0041] Fig. 1 shows a vehicle 100 traveling on a roadway 110. The roadway 110 has at least one road marking 111 (e.g., a guide line, a warning line, a lane boundary, a lane boundary, an exit line, etc.). The road markings 111 can have different properties (particularly with respect to the visibility of the road marking 111 and / or with respect to the reflectivity of light).

[0042] The vehicle 100 comprises at least one environmental sensor 104, in particular at least one image camera or at least one image sensor, which is configured to capture sensor data, in particular image data, relating to the lane marking 111 or the roadway 110. A control unit 101 of the vehicle 100 can be configured to operate one or more actuators 105 of the vehicle 100 depending on the sensor data. For example, depending on the sensor data, a warning can be issued to a driver of the vehicle 100 if it is detected that the vehicle 100 is approaching the lane marking 111 or is crossing the lane marking 111. Alternatively or additionally, a lateral guidance actuator 105 (e.g., a steering device) of the vehicle 100 can be operated depending on the sensor data in order to automatically guide the vehicle 100 from a first lane into a second lane.The driver of the vehicle 100 can thus be assisted in the lateral guidance of the vehicle 100 on the basis of the sensor data from one or more environmental sensors 104.

[0043] The control unit 101 can be configured, in particular by applying an image processing algorithm, to detect the lane marking 111 based on the acquired image data. In this case, the value of a quality measure (i.e., quality data) can also be determined, which indicates the reliability or quality with which the lane marking 111 can be detected. Typically, a lateral guidance assistant of the vehicle 100 can only be operated if the value of the quality measure is greater than a quality threshold. On the other hand, the lateral guidance assistant is typically aborted (of which the driver of the vehicle 100 can be informed via a user interface of the vehicle 100). A relatively poor quality of the acquired image data thus leads to a reduced availability of a lateral guidance assistant.

[0044] The quality of the captured image data may depend on the visibility conditions in the immediate vicinity of the vehicle 100. For example, relatively dense fog and / or relatively heavy rain may result in a lane marking 111 not being detected or only being detected relatively poorly based on the image data from an image sensor 104. As a result, the availability and / or reliability of a lateral guidance assistant decreases.

[0045] A vehicle 100 typically includes one or more lighting units 102 configured to illuminate the roadway 110 in front of the vehicle 100. Exemplary lighting units 102 are a headlight and / or a fog light. A lighting unit 102 may be configured to change one or more properties of the light 106 emitted by the lighting unit 102. Exemplary properties are • the direction of the emitted light 106; • the intensity of the emitted light 106; and / or • a spectral composition of the emitted light 106.

[0046] The control unit 101 of the vehicle 100 can be configured to operate a lighting unit 102 of the vehicle 100 in such a way that the quality of the sensor data acquired by the surroundings sensor 104 is increased, in particular maximized. This can increase the reliability and / or availability of a lateral guidance assistant.

[0047] The vehicle 100 can, for example, comprise an environmental sensor 103 configured to acquire sensor data relating to the visibility conditions in the surroundings of the vehicle 100. The environmental sensor 103 can, for example, comprise a light sensor and / or a rain sensor. The lighting unit 102 of the vehicle 100 can then be operated depending on the sensor data from the environmental sensor 103. In particular, one or more properties of the emitted light 106 can be adapted depending on the sensor data from the environmental sensor 103. In this way, the quality of the image data acquired by the environmental sensor 104 and thus the reliability and / or availability of a lateral guidance assistant can be increased.

[0048] The control unit 101 of the vehicle 100 can be configured to access lighting characteristics. The lighting characteristics can have been determined experimentally in advance. The lighting characteristics can comprise or indicate a mapping between sensor data from the one or more environmental sensors 103, on the one hand, and properties of the one or more lighting units 102 to be used, on the other hand. In this case, the lighting characteristics can, in particular, indicate the properties of the one or more lighting units 102 that, given the visibility conditions in the surroundings of the vehicle 100 indicated by the sensor data from the one or more environmental sensors 103, result in the highest possible, in particular the maximum possible, value of the quality measure for detecting a lane marking 111.

[0049] The control unit 101 can be configured to determine current sensor data from one or more environmental sensors 103. Furthermore, based on the illumination characteristics and the current sensor data, the optimized properties of the light 106 emitted by a lighting unit 102 can be determined. The lighting unit 102 can then be controlled to emit light 106 with the determined properties. This can increase the quality of the image data acquired by the environmental sensor 104 and thus the reliability and / or availability of a lateral guidance assistant.

[0050] Alternatively or additionally, the control unit 101 can be configured to adapt the operation of a lighting unit 102 of the vehicle 100 to the current visibility conditions within the framework of an (iterative) learning phase in order to increase the quality of the acquired image data. For this purpose, quality data relating to the quality of the image data can be determined based on the acquired image data from the one or more environmental sensors 104. The quality data can, for example, include the above-mentioned value of the quality measure for the reliability and / or quality of an image processing algorithm.

[0051] A lighting unit 102 of the vehicle 100 can then be operated depending on the quality data. In particular, one or more properties of the emitted light 106 can be changed. Image data can then be acquired, and updated quality data can be determined based on the acquired image data. Thus, one or more properties of the emitted light 106 can be adjusted iteratively to improve, in particular, optimize, the quality of the acquired image data.

[0052] Such an iterative learning process makes it possible to increase the quality of the image data acquired by the environment sensor 104 and thus the reliability and / or the availability of a lateral guidance assistant in a particularly efficient manner (in particular, if necessary, without using an additional environment sensor 103).

[0053] As stated above, the optical detection of road markings 111 typically depends on the respective visibility conditions (e.g., the current weather, day or night, etc.). Furthermore, the quality and / or type of a road marking 111 typically influences the quality of the optical detection of road markings 111.

[0054] By adjusting the light 106 emitted by the one or more lighting units 102 of the vehicle 100 (e.g. by using a high beam assistant with adaptive light cone control), a targeted illumination of a lane marking 111 can be effected in order to improve the visibility quality and the visibility range for the automatic detection of the lane marking 111.

[0055] Fig. 2a shows a flowchart of an exemplary method 200 for operating a driving function of a vehicle 100. The driving function can be configured to perform at least partially or fully automated longitudinal and / or transverse guidance of the vehicle 100 and / or to assist a driver of the vehicle 100 in the longitudinal and / or transverse guidance of the vehicle 100. The method 200 can be executed by a control unit 101 of the vehicle 100.

[0056] The method 200 includes determining 201 environmental data relating to visibility conditions on a roadway 110 located in front of the vehicle 100 in the direction of travel. The environmental data can be acquired using one or more environmental sensors 103 of the vehicle 100. The environmental data can describe a specific visibility situation (e.g., fog, precipitation, daylight, night, etc.).

[0057] Furthermore, the method 200 includes operating 202 at least one lighting unit 102 of the vehicle 100, wherein the lighting unit 102 is configured to emit light 106 onto the roadway 110 located in front of the vehicle 100 in the direction of travel. The lighting unit 102 can be operated depending on the ambient data and depending on lighting characteristics.

[0058] The lighting characteristics can be determined in advance, for example, as part of a large number of measurements, and stored on a memory unit of the vehicle 100. The lighting characteristics can indicate different properties or different parameter values ​​of one or more properties of the light 106 emitted by the lighting unit 102 for different values ​​of the ambient data or for different visibility situations. Thus, the roadway can be illuminated (adapted to the current visibility situation).

[0059] In addition, the method 200 comprises the acquisition 203 of image data relating to the roadway 110 located in front of the vehicle 100 in the direction of travel. Due to the fact that the roadway is specifically illuminated by the light of the at least one lighting unit 102, the quality of the acquired image data can be increased (compared to an illumination that is not adapted to the visibility conditions).

[0060] The image data can be acquired using one or more environmental sensors 104 (in particular, using one or more cameras). The illumination characteristics can depend on the one or more environmental sensors 104 used to acquire the image data. In particular, the illumination characteristics can depend on one or more properties of an image camera or image sensor used to acquire the image data. Example properties include: sensitivity of the image camera, dynamic range of the image camera, optical resolution of the camera, pixel size of the individual pixels of the camera, etc.

[0061] Furthermore, the method 200 includes operating 204 the driving function based on the acquired image data. In particular, one or more lane markings 111 can be detected based on the image data. The driving function (in particular a lateral guidance assistant) can then be operated based on the one or more detected lane markings 111.

[0062] Fig. 2b shows another method 210 for operating a driving function of a vehicle 100. The method 210 can be executed by a control unit 101 of the vehicle 100. The aspects described with respect to the method 200 are also applicable to the method 210 (or vice versa).

[0063] The method 210 comprises capturing 211 image data relating to a roadway 110 located in front of the vehicle 100 in the direction of travel. Furthermore, the method 210 comprises determining 212 quality data relating to a quality of the captured image data for use in the driving function. The quality data can indicate how well the captured image data is suited for operating the driving function. In particular, the quality data can indicate the reliability and / or quality with which a road marking 111 can be detected based on the captured image data.

[0064] Furthermore, the method 210 comprises operating 213 at least one lighting unit 102 of the vehicle 100 depending on the quality data. The lighting unit is configured to emit light 106 onto the roadway 110 located in front of the vehicle 100 in the direction of travel. By changing one or more properties of the emitted light 106, properties of the captured image data can be changed (since the illumination of the roadway 110 captured by the image camera 104 changes). The lighting unit 102 can be operated such that the quality of the captured image data indicated by the quality data is increased for use in the driving function. For this purpose, the method 210 can be repeated iteratively to gradually increase the quality of the captured image data.

[0065] In addition, the method 210 includes operating 214 the driving function based on the acquired image data.

[0066] The measures described in this document can improve the automatic detection of lane markings 111. As a result, the availability of (automatic) lateral guidance of a vehicle 100 can be increased, particularly in the dark or in poor weather conditions.

[0067] The present invention is not limited to the embodiments shown. In particular, it should be noted that the description and figures are intended only to illustrate the principle of the proposed methods, devices, and systems.

Claims

[1] Method (200, 210) for operating a driving function of a vehicle (100); wherein the driving function is configured to carry out an at least partially automated lateral guidance of the vehicle (100) and / or to assist a driver of the vehicle (100) in the lateral guidance of the vehicle (100); wherein the method (200, 210) comprises, - Determining (201) environmental data relating to visibility conditions on a roadway (110) located in front of the vehicle (100) in the direction of travel; wherein the environmental data indicate a specific visibility situation from a plurality of predefined, different visibility situations; wherein the different situations differ with respect to a density of fog and / or an amount of precipitation; - Operating (202) at least one lighting unit (102) of the vehicle (100), which is configured to emit light (106) onto the roadway (110) located in front of the vehicle (100) in the direction of travel, as a function of the determined specific visibility situation and as a function of lighting characteristics; wherein the lighting characteristics indicate different properties of the light (106) to be emitted by the lighting unit (102) for the different visibility situations; - capturing (203) image data relating to the roadway (110) in front of the vehicle (100) in the direction of travel; - detecting at least one lane marking (111) based on the acquired image data; and - Operating (204) the driving function depending on the detected lane marking (111). [2] Method (200, 210) according to claim 1, wherein - a specific value of the ambient data indicates the specific visibility situation, and wherein the illumination characteristics for the specific situation indicate the properties of the light (106) to be emitted by the lighting unit (102), by means of which the quality of the captured image data for use in the context of the driving function is increased at least on a statistical average when the specific visibility situation exists; and / or - the lighting characteristics are stored on a memory unit of the vehicle (100); and / or - the lighting characteristics were determined experimentally in advance. [3] Method (200, 210) according to one of the preceding claims, wherein - the illumination characteristics depend on one or more properties of an environmental sensor (104), in particular an image sensor, for capturing the image data; and - which in particular comprise one or more properties of the environment sensor (104), - a sensitivity of the environment sensor (104); - a dynamic of the environment sensor (104); - a pixel resolution of the environment sensor (104); and / or - a pixel size of pixels of the environment sensor (104). [4] Method (200, 210) according to one of the preceding claims, wherein the properties of the light (106) comprise one or more of - a local distribution of the light (106) on the roadway (110); and / or - an intensity of the light (106), in particular a spatial distribution of the intensity of the light (106) on the roadway (110); and / or - a spectral composition of the light (106); and / or - a direction and / or orientation of a luminous cone of light (106). [5] Method (200, 210) according to one of the preceding claims, wherein the environmental data comprises - sensor data of a light sensor (103) of the vehicle (100); and / or - sensor data of a rain sensor (103) of the vehicle (100); and / or - sensor data from an image camera (104) of the vehicle (100); and / or - Data from a Car-to-X message received by the vehicle (100). [6] Method (200, 210) according to one of the preceding claims; wherein the method (200, 210) comprises - determining (212) quality data relating to a quality of the acquired image data for use in the driving function; and - Operating (213) the lighting unit (102) of the vehicle (100) in such a way that the quality of the captured image data indicated by the quality data is increased for use in the context of the driving function. [7] Method (200, 210) according to claim 6, wherein the lighting unit (102) is operated such that one or more properties of the emitted light (106) are adjusted such that the quality of the acquired image data indicated by the quality data is increased for use in the driving function. [8] The method (200, 210) of claim 7, wherein the method (200, 210) comprises repeating the steps of acquiring (211) image data, determining (212) quality data, and adjusting the one or more properties of the light (106) to iteratively increase the quality of the acquired image data indicated by the quality data for use in the driving function. [9] Method (200, 210) according to one of claims 6 to 8, wherein the quality data indicate with which quality and / or reliability a road marking (111) of the roadway (110) can be detected on the basis of the acquired image data. [10] Method (200, 210) according to one of claims 6 to 9, wherein the lighting unit (102) is operated such that an intensity distribution of the light (106) is adapted depending on the quality data. [11] Method (200, 210) according to one of claims 6 to 10, wherein the method (200, 210) comprises - detecting an area within the acquired image data in which a lane marking (111) of the lane (110) is reproduced; and - Operating the lighting unit (102) such that an intensity of the emitted light (102) is increased at the area of ​​the roadway (110) indicated by the acquired image data. [12] Method (200, 210) according to one of the preceding claims, wherein - the driving function includes a lateral guidance assistant; and / or - the driving function is designed to assist the driver of the vehicle (110) when changing lanes; and / or - the driving function is designed to assist the driver of the vehicle (110) in maintaining a lane of the roadway (110). [13] Method (200, 210) according to one of the preceding claims, wherein - the method (200, 210) comprises predicting a course of the roadway (110) lying in front of the vehicle (100) in the direction of travel; and - the at least one lighting unit (102) of the vehicle (100) is operated depending on the predicted course of the roadway (110). [14] Control unit (101) for operating a driving function of a vehicle (100); wherein the driving function is configured to carry out an at least partially automated lateral guidance of the vehicle (100) and / or to assist a driver of the vehicle (100) in the lateral guidance of the vehicle (100); wherein the control unit (101) is configured, - to determine environmental data relating to visibility conditions on a roadway (110) located in front of the vehicle (100) in the direction of travel; wherein the environmental data indicate a specific visibility situation from a plurality of predefined, different visibility situations; wherein the different situations differ with regard to a density of fog and / or an amount of precipitation; - to operate at least one lighting unit (102) of the vehicle (100) depending on the determined specific visibility situation and depending on lighting characteristics; wherein the lighting unit (102) is configured to emit light (106) onto the roadway (110) located in front of the vehicle (100) in the direction of travel; wherein the lighting characteristics indicate different properties of the light (106) to be emitted by the lighting unit (102) for the different visibility situations; - to acquire image data relating to the roadway (110) in front of the vehicle (100) in the direction of travel; - to detect at least one road marking (111) on the basis of the acquired image data; and - to operate the driving function depending on the detected lane marking (111).

Images