Method for automatically controlling at least one vehicle function of a vehicle and notification system for a vehicle

Abstract

Method for automatically controlling at least one vehicle function of an ego-vehicle (10) based on at least one optical notification signal (50, 52), in particular a warning signal, with regard to a traffic situation in a vehicle environment (L1 - L3) of the ego-vehicle (10), in particular with regard to a potential hazard situation, wherein the optical notification signal (50, 52) is output by an optical output device (48) on an output surface in a vehicle environment (B1, B2) detected by at least one sensor device (12) for detecting the vehicle environment (L1 - L3) of the ego-vehicle (10), in particular as a spatially resolved representation, comprising: - Receiving environmental data, in particular spatially resolved data, determined by at least one sensor device (12) with regard to the detected vehicle environment (B1, B2); - Determining at least one environmental geometry parameter in relation to the output surface based on the determined environmental data, wherein a 3D model for at least one section of the vehicle environment is determined based on the determined environmental data and the environmental geometry parameter is determined based on the 3D model; - Processing data characteristic of the environment data by means of an evaluation device (18) and thereby determining at least one notification parameter which is characteristic of the optical notification signal, in particular of a meaning of the optical notification signal in relation to the traffic situation; - Providing a message evaluation signal to control the vehicle function depending on at least one notification parameter.

Description

[0001] The present invention relates to a method for the, in particular automatic, control of at least one vehicle function of an (ego) vehicle, particularly based on at least one optical notification signal, in particular a warning signal, with regard to a traffic situation in the vehicle environment of the (ego) vehicle, wherein the optical notification signal is output by an optical output device in a vehicle environment detected by at least one sensor device for detecting the vehicle environment of the (ego) vehicle, in particular as a spatially resolved representation. The present invention further relates to a notification system for an (ego) vehicle.

[0002] With increasing digitalization and the integration of projection systems and displays in vehicles, the density of information in traffic areas is rising. These systems present road users with a multitude of symbols and / or warning and information graphics that are "quickly" and "unambiguously" understandable to humans.

[0003] These representations are not currently standardized and are highly dependent on the specific design of each manufacturer and the target market. In human perception, slight differences from what is learned can be abstracted within the relevant context (e.g., a familiar language but an unfamiliar dialect). For machine processing and especially analysis, even slight variations in graphics, patterns, or symbols can lead to erroneous results.

[0004] The display of traffic signs (e.g., warning and regulatory signs) by means of projection or via stationary or mobile vehicle displays and infrastructure displays is not permitted under current legislation - this is reserved exclusively for state authorities.

[0005] The design of graphics displayed on vehicle screens to provide information about traffic situations or warn of hazards is the responsibility of the vehicle manufacturers. Each graphic design requires separate approval from testing authorities, documenting a clear graphic differentiation from official traffic signs. Since there is (currently) no uniform design guideline for this type of graphic, and each vehicle manufacturer uses its own design language, differences in the graphics arise. For example, the same meaning is sometimes represented by different graphic styles.

[0006] US Patent 2020 / 0110948 A1 discloses a driver assistance system for providing traffic information to a driver. The system utilizes sensors such as a camera, radar, or LiDAR sensor to detect objects in the vehicle's surroundings, such as traffic lights, trees, and the like. Based on the vehicle's position on the road and sensor data, visual information relating to an environmental model of the area in which the vehicle is currently positioned can be determined and displayed. Image data of an object in the environment can be obtained either from the vehicle's own sensors or from other vehicles via V2V communication.

[0007] US Patent 10,252,721 B1 discloses a method for controlling vehicles in a convoy. This method involves projecting a status message onto the ground between two vehicles in the convoy for a vehicle not belonging to the convoy that wishes to merge between them. This is achieved by controlling the vehicle system of the following vehicle to perform the projection.

[0008] US patent 10,093,224 B2 discloses a lighting device for a vehicle with a light output unit for generating light that illuminates an exterior area of ​​the vehicle. For example, weather-related or navigation-related information is projected onto a section of the roadway in front of the vehicle in the direction of travel, for the driver of the vehicle.

[0009] From DE 10 2008 036 219 A1, a method for detecting objects in a vehicle's environment is known. In this method, an image area is compared with a set of features of an object to be identified. The image area and / or the set are transformed into a virtual perspective using a perspective transformation. This yields a transformed or untransformed image area and a transformed or untransformed set of features. A similarity measure between several features of the first-mentioned area and several features of the first-mentioned set is determined by comparing the latter-mentioned area with the latter-mentioned set of features. After successful object detection, the data is used as input for a driver assistance system.

[0010] From DE 10 2018 218 038 A1 a system for projecting informative content for a motor vehicle is known, which has environmental sensors, a control system and at least its projection device for projecting content.

[0011] From DE 10 2006 050 548 A1 a method for warning other road users is known in which a projection object is projected from a vehicle as a warning to another road user outside the vehicle.

[0012] German patent DE 10 2012 212 091 A1 discloses a system and a method for processing license plate image data. In this process, an image containing a license plate is received, any distortion of the image is corrected, and the image is iteratively processed to optimize its quality.

[0013] The present invention is based on the objective of overcoming the disadvantages known from the prior art and providing a method for the automatic control of at least one vehicle function as well as a reliable notification system which provides the fastest and most reliable detection and evaluation of notification signals, in particular warning signals, transmitted in a vehicle environment.

[0014] The object of the invention is achieved by the subject matter of the independent claims. Advantageous embodiments and further developments of the invention are the subject matter of the dependent claims.

[0015] In an inventive (preferably computer-implemented) method for the, in particular automatic, control of at least one vehicle function of an ego-vehicle and / or for the transmission and / or for the detection of at least one notification based on at least one optical notification signal relating to a traffic situation in a vehicle environment of the ego-vehicle, the optical notification signal is or is output by an optical output device onto an output surface in a vehicle environment detected by at least one sensor device for detecting the vehicle environment of the ego-vehicle, in particular as a spatially resolved and / or graphic representation.

[0016] Preferably, the optical output device is an external output device in relation to the ego-vehicle. In other words, the graphically represented information output as an optical notification signal comes from an external source.

[0017] The output area is, in particular, a region of the vehicle's surroundings, especially outside the ego-vehicle. Preferably, the output area is a display surface and / or a projection surface in the vehicle's surroundings, onto which the visual notification signal is displayed or projected. For example, the output area could be a section of the roadway or a section of the shoulder that serves as a projection surface for the visual notification signal. It is also possible that the output area is a display surface and / or projection surface of a stationary and / or mobile vehicle and / or infrastructure output device (in particular, a stationary and / or mobile vehicle and / or infrastructure display).For example, it is possible that the output surface is a display surface and / or projection surface of a vehicle different from the ego vehicle.

[0018] Preferably, the output area corresponds exactly to the area in which the optical notification signal is (graphically) displayed or output as a graphic element. In particular, the outline of the output area corresponds to the outline of the output representation of the optical notification signal.

[0019] Preferably, the traffic situation is a current traffic situation. However, it is also possible that it is a predicted (future) traffic situation.

[0020] Preferably, the visual notification signal is a warning signal, particularly with regard to road safety. More preferably, the visual notification signal indicates a potential hazard, for example, for the (self-driving) vehicle and / or an occupant or user of the (self-driving) vehicle and / or another road user and / or another vehicle. However, it is also conceivable that it could be information relating to a destination and / or a traffic situation, such as parking instructions and / or information related to finding a parking space.

[0021] According to the invention, environmental data, particularly spatially resolved data, determined by the sensor device with respect to the detected vehicle environment (especially by a preferably processor-based notification system, which is preferably described in more detail below) is received (particularly within a computer-implemented process step). "Receiving" can be understood as data transmission, for example, via a digital data exchange and / or via a (at least partially and preferably entirely) wired and / or wireless network. Furthermore, "receiving" can also be understood, particularly within the vehicle, as forwarding and / or retrieving environmental data determined and / or recorded by the sensor device.

[0022] Furthermore, the procedure (especially in a computer-implemented procedure step) includes determining at least one environmental geometry parameter in relation to the output surface based on the determined environmental data.

[0023] The environmental geometry parameter is preferably a geometric parameter such as a projection angle and / or a display angle under which the optical notification signal is output (in particular displayed and / or projected) on the output surface, a parameter characteristic of a geometry of the output surface, and / or a parameter characteristic of a (longitudinal) extension in at least one direction and preferably in at least two mutually perpendicular directions of the output surface, and / or a parameter characteristic of a recording angle (in particular a viewing angle) of the at least one sensor device of the ego vehicle (in particular with respect to the output surface), and / or a parameter characteristic of a distance of the ego vehicle from the output surface.Preferably, the environmental geometry parameter is characteristic of a geometric arrangement between the ego vehicle and the optical output device and / or between the ego vehicle and the output surface and / or between the output surface and the optical output device and / or between the ego vehicle and the optical output device and the output surface.

[0024] Furthermore, the method (particularly in a computer-implemented step) comprises processing data characteristic of the environmental data using an evaluation unit (particularly a processor-based unit). This processing, and the determination of at least one notification parameter depending on the (at least one) environmental geometry parameter, further refines the method. This parameter is characteristic of the optical notification signal, and in particular of its meaning in relation to the traffic situation. Preferably, the data characteristic of the environmental data are the environmental data themselves, and in particular, raw sensor data and / or data derived from the (raw) sensor data acquired and / or generated by the at least one sensor device.

[0025] Preferably, at least one message evaluation signal is provided for controlling the vehicle function (and / or for issuing warnings) depending on at least one notification parameter (particularly in a computer-implemented process step). It is conceivable that the message evaluation signal is a signal to be transmitted to a road user, such as an occupant of the (ego) vehicle and / or another road user and / or a different vehicle.

[0026] Preferably, at least one vehicle function is controlled and / or executed, particularly automatically, depending on the message evaluation signal.

[0027] The proposed method offers the advantage that the determined environmental geometry size can be taken into account when extracting information, hints, and / or warnings from projected symbols and graphics displayed on other screens. This allows for the advantageous consideration of the size of the display, its perspective, and / or any distortion of the visual notification signal, thereby enabling the extraction of information, hints, or warnings regardless of the size, perspective, and distortion of the displayed symbols and graphics.

[0028] In a preferred method, the at least one environmental geometry parameter is the spatial position of the ego-vehicle relative to its surroundings. In other words, the (especially relative) position of the (own) ego-vehicle relative to its surroundings or the projection surface is advantageously determined. From this, a (relative) position and / or orientation of the ego-vehicle relative to the output device and / or the output surface can be determined.

[0029] In a preferred method, at least one environmental parameter is the relative position of the ego-vehicle to the output surface. This advantageously allows the viewing angle and distance of the ego-vehicle to the output surface to be determined and / or taken into account when determining the notification size.

[0030] Preferably, the relative position of the ego-vehicle in relation to the vehicle's surroundings and / or the output area is determined using environmental data, which is also used to determine the notification size. Alternatively or additionally, the relative position of the ego-vehicle (towards the output area and / or in relation to the vehicle's surroundings) is determined using (especially supplementary) sensors for position determination, which are selected from a group that includes an inertial measurement unit (IMU), in particular a gyroscope, a global positioning system (GPS), a differential global positioning system (DGPS), suspension travel sensors, and the like, as well as combinations thereof.

[0031] Preferably, the environmental parameter is a projection and / or display angle and distance of the optical output device to the output surface. This allows for consideration of a distorted representation due to the output angle and / or a size of the optical notification signal influenced by the output distance (especially a compressed size).

[0032] In a preferred method, the at least one environmental geometric parameter is a (spatial) (longitudinal) extent of the output surface along at least one direction, and preferably at least two (spatial) (longitudinal) extents of the output surface along two mutually perpendicular directions, or parameters characteristic of these. From this, a degree of compression and / or stretching (e.g., of an optical notification signal output in a standardized size) can be determined. It is also conceivable that the environmental parameter is a parameter characteristic of the ratio between a (spatial) longitudinal extent of the output surface and a (spatial) extent in a perpendicular (lateral) direction. From this, for example, a projection and / or output angle can be deduced and taken into account when determining the notification size.

[0033] In a preferred method, the at least one environmental geometry parameter is a topographic parameter of the output surface, which is in particular selected from a group of topographic parameters that are characteristic of unevenness, curvature, irregularities, a slope, a surface structure, a surface roughness, or a surface property, especially a surface finish, combinations thereof, or the like. This offers the advantage that distortions in the representation of the optical notification signal on the output surface caused by this topographic parameter of the output surface can be taken into account when determining the notification parameter or when extracting the information.

[0034] It is also conceivable that a material property (such as reflectivity and / or absorption capacity) of the output surface (at least partially, and preferably of the entire output surface) is determined. From this, an optical representation of the optical notification signal can preferably be inferred based on the material property. The material properties of typical ground surfaces in the vehicle environment of the ego vehicle can be retrieved and taken into account in a storage device. It is conceivable that the determined environmental data could be evaluated, particularly using a computer vision method, to determine which object in the vehicle environment the output surface belongs to. For example, the computer vision method could recognize that the output surface is part of a roadway or part of a sidewalk.

[0035] It is also conceivable that two or more of the (especially the aforementioned) environmental geometry parameters are determined and the notification size is determined depending on the two or more environmental geometry parameters.

[0036] In a preferred method, a 3D model for at least one section of the vehicle's surroundings is generated based on the determined environmental data, and the environmental geometry is determined based on this 3D model. Preferably, the environmental geometry is determined solely based on the 3D model. In a preferred method, the 3D model includes the output surface. Preferably, the output surface is highlighted or marked within the 3D model.

[0037] Generating a 3D model offers the advantage that all geometric relationships between the ego vehicle and / or the output surface and / or the output device can be derived from it, and corresponding environmental geometry parameters can be determined.

[0038] Preferably, the 3D model includes the optical output device and / or the output surface (at least partially and preferably completely). This allows the projection and / or display angle and distance of the output device to be determined relative to the output surface.

[0039] In a preferred method, the 3D model, in particular a detailed 3D model, is determined based on environmental data using at least one 3D model generation device selected from a group comprising a LiDAR sensor, a stereo camera system, a system for projected texture stereo vision or pattern projection with 3D image processing, a system for using a so-called "Structure from Motion" method (abbreviated "SfM," for obtaining 3D information by overlapping time-shifted images), a TOF camera (TOF for "time of flight," i.e., in particular a 3D camera system that measures distances using a time-of-flight method), and the like, as well as combinations thereof. The aforementioned sensor data can also be used to determine the (own), in particular relative, position of the ego-vehicle to its environment and / or to the output surface.

[0040] Preferably, the (detailed) 3D model includes unevenness and / or curvature and / or (general) irregularities of the vehicle environment and in particular the road surface and / or the traffic environment and / or the surroundings.

[0041] Preferably, at least one optical sensor device or a multitude of optical sensor devices (e.g. cameras) are used to detect the vehicle's surroundings.

[0042] In a preferred method, monocular depth information (in particular, the monocular depth information contained in the (camera) images of the optical sensors) is determined based on spatially resolved environmental data, and the 3D model is then generated based on this. Preferably, the 3D model is an abstract and / or approximate 3D model of the environment or the vehicle environment (of the ego-vehicle) and / or the output surface (in particular, the projection and / or display surfaces).

[0043] Preferably, the monocular depth information consists of a texture density gradient and / or a shadow and / or parallel lines and / or a perspective.

[0044] The extraction of 3D information can be performed using classical computer vision algorithms or as a separate and / or upstream network using artificial intelligence (AI) (or machine learning). Preferably, 3D information for generating or determining the 3D model is generated using a machine learning model, which is particularly trainable. The model preferably comprises a set of parameters, particularly trainable ones, which are set to values ​​learned as a result of a training process.

[0045] Preferably, a (particularly relative) position of the ego vehicle (especially in relation to the output surface) is determined from the abstract or approximated 3D model of the environment.

[0046] Preferably, the captured environmental data (in relation to the output area) or data derived from it is preprocessed depending on the size of the environmental geometry. This can essentially correct geometrically induced distortions and / or rotations in the optical notification signal, or rectify rotational misalignment. Furthermore, preprocessing can correct perspective distortions such as reduction and / or enlargement. This advantageously results in faster extraction of the notification size from the preprocessed environmental data.

[0047] Preferably, the evaluation unit processes the data characteristic of the environmental data to determine at least one notification parameter (in particular as a function of the environmental geometry parameter) using a machine learning model, which is particularly trainable. Preferably, the model comprises a set of parameters, which are particularly trainable, and which are set to values ​​learned as a result of a training process.

[0048] Preferably, data characteristic of the environment data are first processed (especially by the evaluation unit) on the basis of the environment geometry size, before the evaluation unit (further) processes the data characteristic of the environment data using the machine learning model and determines at least one notification size from this.

[0049] Preferably, the method includes AI-based symbol recognition and / or recognition of warning and / or informational graphics, particularly in projections and on displays.

[0050] In a preferred method, the optical output device is an optical output device, in particular a projection module and / or a display device, of another vehicle (hereinafter also referred to as the "surrounding vehicle") from the vehicle environment of the ego vehicle, which is preferably suitable and intended for outputting the notification signal into the vehicle environment, in particular into an externally perceptible area and / or on an external vehicle surface (such as a display or a display unit of the other vehicle) and / or a ground surface. This advantageously enables external communication between two vehicles via the output (and reception) of an optical notification signal.This makes it possible to transmit notifications via a non-digital communication channel, so that preferably no communication protocol, as is required for network-based communication channels, is needed for transmission.

[0051] Preferably, the ego-vehicle has at least one sensor device for detecting the vehicle's surroundings. In other words, the at least one sensor device for detecting the vehicle's surroundings is preferably part or an integral component of the ego-vehicle and / or (particularly not removable without damage) arranged in and / or on the ego-vehicle. However, it is also conceivable that the at least one sensor device is an external sensor device with respect to the ego-vehicle, which is not arranged on the ego-vehicle and which transmits environmental data, particularly with respect to the vehicle's surroundings, to the ego-vehicle and in particular to the notification system and / or to an evaluation unit (preferably of the vehicle and / or the notification system).

[0052] In other words, an optical, and in particular spatially resolved, notification signal is preferably output in the (especially external) vehicle environment of the ego-vehicle, preferably by the optical output device. Preferably, the optical output is such that the optical notification signal is perceptible and / or detectable by the sensor device for detecting the vehicle environment of the ego-vehicle.

[0053] Preferably, the sensor device detects (at least temporarily) at least an area of ​​the vehicle's surroundings, and in particular an area of ​​the vehicle's surroundings in which the optical notification signal is emitted, displayed, and / or shown. Preferably, the sensor device determines and / or generates environmental data from or relating to the detected vehicle's surroundings (in which the optical notification signal is emitted, displayed, and / or shown). Preferably, the environmental data includes data relating to the (emitted), and in particular spatially resolved, optical notification signal. This means, in particular, that the environmental data is (at least partially) characteristic of the optical notification signal.

[0054] Preferably, the visual notification signal is output in such a way that it is (at least temporarily and at least partially) (visually) perceptible to a user, in particular a driver, of the (ego) vehicle. For example, the visual notification signal can be output and / or displayed on a road surface and / or on a display surface of another vehicle located in the vicinity of the vehicle.

[0055] In particular, it is proposed that the notification signal be transmitted to the (ego) vehicle and especially to the evaluation unit via an optical communication path. The proposed evaluation using a trainable machine learning model enables reliable evaluation of various optical notification signals with the same meaning. For example, different optically output notification signals, such as symbols representing the same notification, such as the same warning message, may have different designs depending on the manufacturer or brand. By using a trained or trainable machine learning model, it is possible to recognize a wide variety of different designs and / or symbols that are nevertheless synonymous with the traffic situation.

[0056] Preferably, the sensor device captures a spatially resolved and preferably graphical (and / or two-dimensional) representation of the optical notification signal in the detected vehicle environment (caused by the optical output device).

[0057] Preferably, the sensor device detects a projected representation of the optical notification signal, which is projected onto a projection surface, preferably onto a floor area and / or a roadway area. Preferably, the evaluation device (particularly using a machine learning model) is designed to recognize symbols in the projections and / or displayed (image) elements.

[0058] Preferably, the optical output device displays a graphic (image) element, and in particular a symbol or a graphically designed symbol or emblem. This offers the advantage that these elements can be intuitively, quickly, and reliably recognized by both road users, such as occupants of the (self-driving) vehicle, and by machines.

[0059] Preferably, a (geometric) size, and / or an orientation and / or a distortion and / or a position and / or a shape and / or a brightness and / or a color of the output (projected and / or displayed) optical notification signal (in particular the representation in the projection surface or on the display device) is adjustable and / or (in particular automatically) changeable and / or (in particular automatically) predefinable by the optical output device (in particular the surrounding vehicle). Preferably, the adjustment and / or (automatic) change and / or (automatic) predefinition is carried out depending on a (preferably relative) position of the (ego) vehicle (in particular to the surrounding vehicle and / or to the optical output device) and / or road occupancy and / or type of the (ego) vehicle and / or distance of the (ego) vehicle to the surrounding vehicle and in particular to the optical output device.

[0060] The optical notification signal is preferred, and it is particularly preferred that several (preferably all) optical notification signals in the form of, in particular, legally prescribed and / or standardized signs, preferably traffic signs, and / or (abstracted and / or high-contrast) symbols are displayed by output (in particular via a projection and / or display).

[0061] The at least one optical notification signal, and preferably a multitude of optical notification signals (preferably each), can be output (especially projected and / or displayed) in the form of geometric graphics, such as traffic signs, and / or schematic drawings.

[0062] In principle, all types of symbols and / or graphics can be used that are understandable to a human in the respective context. The visual notification signal is preferably designed or displayed in such a way that it is presented (through projection and / or display) as a symbol and / or graphic and / or icon that is understood by a large number, and preferably by a majority, of people (especially within a given area). This offers the advantage that a user of the (self-driving) vehicle who directly (visually) perceives the displayed notification signal can immediately understand its meaning and, if necessary, react accordingly.

[0063] A display format (in which the visual notification signal is preferably output, in particular projected onto a projection surface and / or displayed by means of a display device) is preferably selected from a group that includes symbols, traffic signs, landmarks, (general, special) warning signs, regulatory signs, signs or symbols for stop requirements, stopping requirements, directions of travel, passing, hard shoulders as lanes, bus stops, taxi ranks, special lanes, traffic prohibitions, speed limits, no-overtaking zones, no-stopping and no-parking zones, and the like, as well as combinations thereof. Such a display format offers the advantage that these warnings can be directly detected not only by the sensor device (in particular the (ego) vehicle) but also by a road user, such as a user of the (ego) vehicle (without requiring evaluation by an evaluation device).

[0064] Preferably, the representation format can be selected from a multitude of representation formats, preferably stored in a storage device of the surrounding vehicle.

[0065] Preferably, the optical notification signal (especially projected, particularly as a graphic and / or symbol) can be characteristic of information about an upcoming traffic situation. In particular, the optical notification signal can be characteristic of an object and / or an area of ​​interest (in relation to a traffic situation) which is obscured by the surrounding vehicle, which is designed to be particularly tall / wide (e.g., SUV, truck, bus, and the like).

[0066] Another preferred example is that the visual notification signal can indicate the presence of other road users and / or the reason for a (particularly current) driving behavior of the surrounding vehicle. For example, the larger vehicle (which in this example represents the surrounding vehicle) stops at a crosswalk to allow pedestrians to cross and projects the information onto the road behind it. Following (self-driving) vehicles recognize the graphic (which, for example, depicts a person crossing a street) and are thus informed that the (surrounding) vehicle has stopped.

[0067] Preferably, the visual notification signal (especially projected, particularly as a graphic and / or symbol) can be characteristic of a driving maneuver (preferably currently being performed and / or intended) (by the surrounding vehicle and / or another vehicle participating in a traffic situation in the vehicle's vicinity). For example, the visual notification signal can be output (especially projected and / or displayed) in the form of at least one (especially schematic) arrow(s) and / or line(s), or the like. This offers the advantage that driving maneuvers (of the surrounding vehicle) can be communicated in the form of arrows, lines, and the like.

[0068] As another preferred example, the optical notification signal can be characteristic of a message to be exchanged between the (ego) vehicle and the surrounding vehicle. For example, the optical notification signal can serve as a substitute for direct communication between two drivers in autonomously driving (ego) vehicles. For example, the optical notification signal (which is emitted by the output device of the surrounding vehicle) can be characteristic of a notification from which it can be deduced that a (or the), in particular (at least partially and preferably fully) autonomously driving (surrounding) vehicle is signaling that it has detected or seen another (ego) vehicle and / or has recognized a planned driving maneuver and / or, for example, is yielding the right-of-way.

[0069] Another preferred example is that the visual notification signal can be characteristic of at least one planned driving maneuver (especially by the surrounding vehicle). This offers the advantage of enabling communication about planned driving maneuvers. For example, when searching for a parking space, the searching (surrounding) vehicle communicates this information into the traffic area or to the surroundings of the (ego) vehicle, preferably to inform others why it might be moving somewhat slower. For example, when pulling out of a parking space, a visual notification signal can be sent out, from which the information can be derived that this (parking) space is about to become free.

[0070] Preferably, the visual notification signal (especially projected, particularly as a graphic and / or symbol) can be characteristic of one or more requests for assistance (especially from the surrounding vehicle) to other road users. For example, a symbol could be displayed or shown from which an indication can be derived (especially by a user of the (ego) vehicle and / or an evaluation unit of the (ego) vehicle) that a vehicle requires assistance, for example due to a breakdown, and / or that an emergency call should be made (or an emergency signal should be sent, especially by the (ego) vehicle), and / or whether everything is OK and, in particular, no assistance is required.

[0071] It is possible that the displayed and / or projected optical notification signal is a static or dynamic (graphic) object or image element, and in particular, that its form changes depending on time.

[0072] In a further preferred method, the training process is based on a training dataset which includes, in particular, legally (or by regulation) prescribed and / or standardized signs, preferably traffic signs, and / or symbols and / or icons, and a characteristic parameter for their meaning in relation to a traffic situation. Preferably, the set of trainable parameters is determined based on this training dataset and / or values ​​are assigned to each parameter. Preferably, the model learns known symbols. This training process is preferably carried out before the trained model is used to process the environmental data or characteristic data and is particularly preferably completed.

[0073] Preferably, a basic (training) dataset is provided, comprising known and / or generally valid symbols and / or, in particular, legally (or by regulation), prescribed and / or standardized signs, preferably traffic signs, and / or icons and / or symbols and (in each case) their meaning or a characteristic value for their meaning in relation to a traffic situation. Preferably, the training process and / or the determination of the parameters (or the setting of values ​​for the model parameters) is based on the basic (training) dataset. Thus, it is advantageous to learn a basic dataset consisting of known / generally valid symbols and their meanings.

[0074] Preferably, the (basic) dataset is enriched with, for example, brand-specific symbols, and preferably, the (basic) dataset includes brand-specific symbols. This offers the advantage that manufacturer-specific variations or different representations and characteristics of the symbols for notification signals with the same or similar meaning (which is what is meant by brand-specific symbols) can be learned and taken into account in later use. For example, two brand-specific symbols might differ in their font, line thickness, or color.

[0075] Preferably, the (basic) dataset is enriched with design-specific graphic elements or symbols, and preferably, the (basic) dataset includes design-specific symbols and / or graphic elements. Design-specific symbols or graphic elements are understood to mean, in particular, two different symbols or graphic designs that convey the same meaning. A dataset consisting of design-specific graphic elements can be learned. For example, the hazard symbols used in Ireland are diamond-shaped with a yellow background and thus differ significantly from the hazard symbols of other European countries, where the hazard symbols chosen as traffic signs are a red-bordered triangle on a white background with the point facing upwards as their basic shape.

[0076] The (base) dataset and / or the training dataset can consist of (purely) photorealistic training data and / or (purely) synthetic training data.

[0077] Preferably, the machine learning model is suitable for executing a (computer-implemented) computer vision procedure and determines in which (computer-implemented) perception and / or acquisition tasks are performed, for example, (computer-implemented) 2D and / or 3D object recognition procedures and / or (computer-implemented) procedures for semantic segmentation and / or (computer-implemented) object classification ("image classification") and / or (computer-implemented) object localization.

[0078] In object classification, an object captured and / or displayed in the environment data (or in the data characteristic of the environment data) is assigned to a (previously trained and / or predefined) class. In object localization, in addition to object classification, the location of an object captured and / or displayed in the environment data (especially in relation to the environment data or its characteristic data) is determined or ascertained, which is marked and / or highlighted, in particular, by a so-called bounding box. In semantic segmentation, a class (for classifying an object) (especially from a predefined set of classes) is assigned to each pixel of the environment data (or its characteristic data) (class annotation).

[0079] Preferably, the (detected and / or displayed) object is an object that is characteristic of the optical notification signal (or its representation and / or mapping in the environmental data). Preferably, the (detected and / or displayed) object corresponds to the environmental data associated with the optical notification signal.

[0080] The classes can (among other things) be a meaning (especially in relation to a traffic situation) of a detected object and / or a notification parameter characteristic of a meaning of the detected object or of a meaning of the (detected and especially displayed) optical notification signal.

[0081] For example, the classes may refer to the respective meaning of different types of hazard and / or warning signs, or to an identification or classification of the recorded object as a specific predefined hazard sign.

[0082] Preferably, a recorded object is classified based on the geometric shape of the object (for example, circular shape, triangular shape, octagonal shape, rectangular shape).

[0083] Preferably, the machine learning model, when processing the environmental data, separates the design, symbol (or graphic sign or element and / or emblem), and meaning (or notification level) (of the detected object). Preferably, a notification level is determined based on the detected meaning, which is characteristic of the meaning of the optical notification signal and, in particular, of the detected spatially resolved representation of the optical notification signal.

[0084] Preferably, the machine learning model is based on an (artificial) neural network (AI - Artificial Intelligence). Preferably, the artificial neural network is fed environmental data (or data derived therefrom) as input. Preferably, the artificial neural network maps the inputs to outputs based on a processing chain that is parameterizable (by the trainable or trained parameters), wherein at least one notification value, which is characteristic of the (detected) optical notification signal, is chosen as the output.

[0085] Such a neural network can be designed, for example, as a deep neural network (DNN), in which the parameterizable processing chain has multiple processing layers, and / or as a convolutional neural network (CNN) and / or a recurrent neural network (RNN). Preferably, the parameterizable processing chain is parameterized during training. Preferably, datasets relating to the (base) datasets described above and / or training datasets are used as training data. Training preferably takes place using supervised learning. However, it would also be possible to train the artificial neural network using unsupervised learning, reinforcement learning, or stochastic learning.

[0086] In a further preferred method, a verification device validates and / or verifies the determined notification level based on a further notification signal, different from the detected optical notification signal, received by at least one communication device of the (ego) vehicle. Preferably, a validation and / or verification of the recognized symbols is performed. This offers the advantage of a redundant second transmission option, which advantageously increases reliability.

[0087] Preferably, the additional notification signal is a non-optical notification signal, i.e., in particular a signal not transmitted via (at least partially) optical communication channels. This advantageously provides a means of verifying the acquisition and / or evaluation of the optical notification signal and increases overall process reliability.

[0088] In a further preferred method, (at least) one additional training step of the machine learning model is performed based on the received environmental data and the plausibility check and / or verification of the determined notification size. Specifically, new symbols and their meanings are learned and recognized by comparison with symbols and / or information data received (essentially) simultaneously via another communication channel, for example, via Car2Car and / or Car2Infrastructure (C2X). This offers the advantage that the already deployed machine learning model is adaptable and improvable. In particular, the accuracy of the detection and evaluation can be further improved, and new symbols, icons, characters, and / or graphic elements (as well as their meanings) can be included and integrated.

[0089] Preferably, for at least one further training step, at least one (in particular, another) training dataset is generated based on the environmental data (captured and / or determined by the sensor device) and / or on the basis of the further notification signal (and in particular depending on the result of the plausibility check and / or the verification). This training dataset preferably contains photorealistic training data.

[0090] Preferably, the (already) trained machine learning model is subjected to a further training step, particularly using sensor data acquired during its use and / or other notification signals, and in particular the values ​​set for the model parameters (which were learned as a result of the training process) after a completed training process are changed.

[0091] It is also conceivable that instead of a further training step, a machine learning model is retrained, which in particular uses the basic training data set and which uses the training data set generated on the basis of the environmental data (captured and / or determined by the sensor device) and / or on the basis of the further notification signal.

[0092] Preferably, the plausibility of the recognized symbols and graphics is verified using other information channels (e.g., Car2X, DAB+, mobile online services). This advantageously increases data quality (such as positional accuracy) and / or reliability. Furthermore, it advantageously achieves independence from hardware interfaces and communication standards.

[0093] In a further preferred method, the additional notification signal is received via a digital communication link and / or via a wireless (in particular private and / or public) network, preferably via Car2Car communication, C2C communication and / or Car2X communication and / or Car2I communication. The network can be a local network, such as a WLAN network.

[0094] Preferably, the captured symbols can be passed on to other road users and / or vehicles (via projection and / or digitally via C2X).

[0095] In a further preferred method, an output signal is provided on the basis of the determined notification size for output (and / or transmission) to at least one other road user and / or another vehicle by an output device of the (ego) vehicle, in particular optical.

[0096] Preferably, the information (e.g., end of traffic jam, hazard) is passed on to other road users optically and / or digitally, for example via a projection / display module on the (ego) vehicle or via Car2X.

[0097] The (ego) vehicle can be in communication with at least one other vehicle, at least indirectly and preferably directly (e.g., via Car2Car, C2C, Car2X, and / or Car2I communication). The notification system and / or evaluation unit can transmit the determined environmental data and / or the detected objects and / or the determined notification parameters at least indirectly (via other road users or infrastructure) and preferably directly to at least one other vehicle.

[0098] At least one determined notification metric and / or message evaluation signal can either be stored locally in the (ego) vehicle or can optionally be uploaded to a cloud.

[0099] Preferably, the detected information / warning message (and / or the determined notification size and / or the determined message evaluation signal) is displayed in at least one display and preferably in displays in the interior (of the (ego) vehicle), particularly preferably via light-emitting diodes (LEDs) and / or via audio signal / message.

[0100] In a further preferred method, an output signal is provided based on the determined notification level for output to at least one occupant of the (ego) vehicle by at least one output device of the (ego) vehicle, in particular optical and / or acoustic. The recognized symbols can thus advantageously be displayed to the occupants of the (ego) vehicle.

[0101] The message evaluation signal, which is to be output in particular to an occupant of the (ego) vehicle, is preferably selected from a group that includes silent notification signals, haptic notification signals, visual notification signals, acoustic notification signals, and combinations thereof. It is possible that the message evaluation signal is output via a contact element of the (ego) vehicle, in particular a seat and / or a seatbelt tensioner, via a mobile device, and / or via a visual display device, such as a screen.

[0102] Preferably, the (ego) vehicle and in particular the evaluation unit (of the (ego) vehicle and / or the external server) determines whether the notification size relates to the roadway selected and / or to be used by the (ego) vehicle and / or is relevant to the traffic safety of the (ego) vehicle.

[0103] Preferably, the sensor device for detecting a vehicle's surroundings (of an (ego) vehicle) is selected from a group of sensors comprising a (color) camera, a front camera, a rear camera, an infrared camera, LiDAR (short for Light Detection and Ranging or Light Imaging, Detection and Ranging), radar, ultrasonic sensors, and the like, as well as combinations thereof. Preferably, the sensor device for detecting a vehicle's surroundings generates spatially resolved (in particular 2D and / or 3D) sensor data (of the vehicle's surroundings of the respective (ego) vehicle).

[0104] In a preferred method, the evaluation unit is an external evaluation unit, in particular a cloud-based and / or an external server. An external server is understood to be, in particular, a server external to the (ego) vehicle, especially a backend server. The external server is, for example, a backend of a vehicle manufacturer or a service provider, which is configured to evaluate environmental data and / or data derived therefrom (in particular, in relation to traffic situations involving a large number of (ego) vehicles) and / or to manage and / or store (determined) notification size(s). The functions of the backend or the external server can be performed on (external) server farms. The (external) server can be a distributed system. The external server and / or the backend can be cloud-based.

[0105] Furthermore, the method includes determining a control variable based on environmental data and / or the message evaluation signal. Preferably, the control variable is a parameter for controlling the acceleration and / or braking behavior of the (ego) vehicle.

[0106] Preferably, the vehicle function is a function of a vehicle component of the (ego) vehicle. Preferably, the vehicle component is selected from a group comprising a vehicle safety system (for example, a braking system), a system for driving the (ego) vehicle, in particular an automatic lateral vehicle control system, a lane keeping system, a lane change assist system, a navigation system, a locking system for a vehicle door and / or a vehicle window, a windshield wiper mechanism, a vehicle locking system, a roof opening mechanism, a sunroof mechanism, an infotainment system, an entertainment system, and / or a comfort system for increasing the driving comfort of an occupant, and combinations thereof.

[0107] The present invention is further directed to a notification system for an ego-vehicle for the automatic control of at least one vehicle function of an ego-vehicle based on at least one optical notification signal, in particular a warning signal, with regard to a traffic situation in a vehicle environment of the ego-vehicle, in particular with regard to a potential hazard situation.

[0108] The optical notification signal is output and / or outputtable from an optical output device onto an output surface within a vehicle environment detected by at least one sensor device for sensing the vehicle surroundings of the ego vehicle, in particular as a spatially resolved representation. The notification system is suitable and designed to receive environmental data, in particular spatially resolved data, determined by the sensor device with respect to the detected vehicle environment.

[0109] According to the invention, the notification system is suitable and designed to determine at least one environmental geometry parameter in relation to the output surface based on the determined environmental data.

[0110] According to the invention, the notification system is suitable and intended to process data characteristic of the environmental data by means of an evaluation device, whereby at least one notification parameter can be determined and / or is determined depending on the size of the environmental geometry, which is characteristic of the optical notification signal, in particular of a meaning of the optical notification signal in relation to the traffic situation.

[0111] Preferably, the notification system is suitable and designed to provide (preferably to a control unit of the (ego) vehicle) a message evaluation signal for controlling the vehicle function depending on at least one notification parameter.

[0112] It is therefore also proposed within the framework of the notification system according to the invention that optical notification signals (such as a warning triangle projected onto the road) emitted (e.g. by a surrounding vehicle) are detected and the notification to be transmitted (e.g. a warning) is recognized (by the evaluation unit).

[0113] Preferably, the notification system is suitable and designed to process data characteristic of the surrounding environment using the evaluation unit, preferably with the aid of a machine learning model, particularly a trainable one. Preferably, the model comprises a set of parameters, particularly trainable ones, which are set to values ​​learned as a result of a training process, and whereby at least one notification parameter can be determined and / or is determined, which is characteristic of the optical notification signal, in particular of the meaning of the optical notification signal in relation to the traffic situation.

[0114] Preferably, the sensor device is part of the notification system and / or an (integral) component of the (ego) vehicle.

[0115] Preferably, a high-definition projector (HDP) is used as the optical output device. Each light source of this high-definition projection system can, for example, be a laser light source and / or an LED light source.

[0116] Preferably, an optical display device, and in particular a display, is provided as the optical output device, preferably arranged on an exterior surface of the vehicle. This is preferably a rear exterior surface of the vehicle (with respect to the vehicle's forward direction). However, it is also conceivable that it is a side exterior surface and / or a front surface of the vehicle. Furthermore, the rear and / or side windows (of the vehicle) can also serve as projection surfaces. The projectors required for this are then preferably located in the interior of the vehicle and are suitable and designed to project onto the window.

[0117] Preferably, the notification system is configured, suitable, and / or intended to execute the procedure described above, as well as all procedural steps already described above in connection with the procedure, either individually or in combination. Conversely, the procedure can be equipped with all features described within the notification system, either individually or in combination.

[0118] The present invention further relates to a vehicle, in particular a motor vehicle, comprising a notification system for a (self-driving) vehicle as described above, according to one embodiment. The (self-driving) vehicle can in particular be a (motorized) road vehicle.

[0119] A vehicle can be a motor vehicle, specifically a driver-operated vehicle ("driver only"), a semi-autonomous vehicle, an autonomous vehicle (e.g., of autonomy level 3, 4, or 5 (according to standard SAE J3016)), or a self-driving vehicle. Autonomy level 5 refers to fully automated vehicles. Preferably, the vehicle is a vehicle from the transportation sector. It can also be a driverless transport system. The vehicle can be driven by a driver or drive autonomously. Furthermore, in addition to a road vehicle, the vehicle can also be an air taxi, an aircraft, or another means of transport or vehicle type, such as an aircraft, watercraft, or rail vehicle.

[0120] The present invention further relates to a computer program or computer program product, comprising program means, in particular a program code, which represents or encodes at least some of the and preferably all of the process steps of the method according to the invention and preferably one of the described preferred embodiments and is designed for execution by a processor device.

[0121] The present invention further relates to a data storage device on which at least one embodiment of the computer program according to the invention or a preferred embodiment of the computer program is stored.

[0122] The present invention has been described in relation to a vehicle. However, the present invention is also transferable to methods and systems in general in machine vision processing (e.g., also in an infrastructure). The applicant reserves the right to claim related subject matter.

[0123] Further advantages and embodiments can be seen from the attached drawings: It shows: Fig. 1. A representation of a traffic situation for the use of a method according to the invention in one embodiment; and Fig. 2 a schematic representation of a preprocessing step of a detected warning message carried out within the framework of a method according to an embodiment of the invention.

[0124] Fig. Figure 1 shows a representation of a traffic situation in which a proposed procedure and a proposed notification system 1 are used. A (surrounding) vehicle 40 in a hazardous situation, such as one on a hard shoulder L3 (as in Fig. 1 (illustrated) a disabled vehicle projects, in particular by means of an optical output device and here a projection device 48, a warning message, here a warning triangle 52 and a warning symbol 50, which warns of a hazard, onto the roadway L2, on which a (following) (following) ego vehicle 10 is preferably located, as well as onto the shoulder L3. In addition, a hazard warning system 42 of the vehicle 40 may also be activated.

[0125] Reference sign 46 indicates an illustration of the projection of the optical notification signal 50 by an optical output device of the surrounding vehicle 48 onto the roadway L2, on which this is displayed as a warning 50.

[0126] The (following) ego vehicle 10 can detect the projected warning message 50 and the projected warning triangle, which are located in the field of view B1 and the field of view B2 of a sensor device 12, implemented here as a camera, by means of the sensor device 12. The sensor device 12, implemented here as a camera for detecting the vehicle surroundings of the ego vehicle 10, can be suitable and intended to record and / or detect the vehicle's front surroundings, which in particular include or contain the notification signals 50 and / or 52.

[0127] Preferably, the following vehicle 10 recognizes the projected / displayed graphic 50, 52, or the symbol, in this case the warning triangle and the hazard warning lights, preferably with the aid of an evaluation unit 30, which is particularly AI-based. A projection with an alternative representation of the information or warning is also recognized. In particular, recognition and plausibility checks of symbols / warnings using AI are possible.

[0128] Reference numbers 14 and 44 identify communication devices of the two vehicles, which enable Car2Car communication for data verification.

[0129] Fig. Figure 2 shows a schematic representation of a step of (data) preprocessing of a detected warning message 54 carried out within the framework of a method according to an embodiment of the invention, preferably by a (following) ego vehicle and particularly preferably by an evaluation device (in particular of the following ego vehicle 10).

[0130] Preferably, an evaluation unit, and particularly preferably an evaluation unit of the following vehicle, performs a rectification and extraction of the communicated information.

[0131] Reference sign 56 indicates the projected warning message 54 after its equalization by an evaluation device (e.g., of the following ego vehicle) and / or a preprocessing device or preprocessing component, in particular AI-based.

[0132] The notification size derived from the warning notice 56 shown (here a warning of a general hazard) can then be transmitted to a breakdown vehicle 58.

[0133] In a first embodiment of the method according to the invention, a detailed (unevenness, curvature, or general irregularities) 3D model of the roadway / traffic environment / surroundings is generated by means of sensors of the ego vehicle 10 (e.g. using LIDAR, stereo camera system, Projected Texture Stereo Vision, Structure from Motion, TOF camera and / or the like).

[0134] The first embodiment further comprises (in particular in a subsequent second step) a determination of its own (ego-vehicle 10) relative position to the environment or the projection surface from the aforementioned sensor data or by means of supplementary sensors for position determination (e.g. by means of an Inertial Measurement Unit (IMU, in particular a gyroscope), (D)GPS, suspension travel sensors and / or the like).

[0135] The first embodiment further comprises (in particular in a subsequent, especially third, step) a detection of the projected / displayed graphic 50 in the images of the optical (environmental) sensors of the vehicle 10.

[0136] The first embodiment further comprises (in particular in a subsequent, especially fourth, step) a perspective correction of the image section 54 (including the contained graphic) based on the previously generated environmental and / or positional information. This preferably results in a corrected optical notification signal 56.

[0137] The first embodiment further comprises (in particular in a subsequent, especially fifth, step) a segmentation and classification of the graphic 56 by means of AI extraction of the information / hints / warnings contained and communicated in the graphic (or the determination of at least one notification size).

[0138] In a second embodiment of the method according to the invention, an optical sensor or several optical sensors (e.g. cameras) are used to detect the vehicle environment.

[0139] In a first step of the second embodiment, an abstract / approximate 3D model of the environment (especially the projection and / or display surfaces) is preferably generated based on the monocular depth information contained in the images from the optical sensors (e.g., texture density gradient, shadows, parallel lines / perspective). The extraction of the 3D information can be performed using classical computer vision algorithms or as a separate or upstream network using AI (machine learning).

[0140] Preferably, the third and especially the subsequent steps of the first embodiment of the method according to the invention follow, since the relative position of the Ego vehicle 10 is already implicitly contained in the data of the first step of the second embodiment (and can be determined).

[0141] The applicant reserves the right to claim all features disclosed in the application documents as essential to the invention, provided they are novel individually or in combination compared to the prior art. It is further noted that the individual figures also describe features which may be advantageous on their own. A person skilled in the art will immediately recognize that a particular feature described in a figure may be advantageous even without incorporating other features from that figure. Furthermore, a person skilled in the art will recognize that advantages may also arise from a combination of several features shown in individual or different figures. Reference symbol list 1 Notification system 2 Vehicle data set 4 users 6 road users 10 vehicles 12 Sensor device 14 Communication device 15 radio receivers 16 Control unit 17 Plausibility check device 18 Evaluation unit, symbol graphic recognition 19 Communication device, Car2X receiver 20 Cloud 22 Environment output device 24 Output device 26 Acoustic output device 30 Evaluation unit 40 vehicles in the vicinity in a dangerous situation 42 Hazard warning lights 44 Communication device 46 Illustration Projection 48 Optical output device, projection module 50, 52 Optical notification signal 54 projected warning message in distorted representation 56 Warning notice after equalization 58 breakdown vehicles B1, B2 Illustration of captured vehicle environment, camera field of view L1, L2 lane L3 side stripes

Claims

[1] Method for automatically controlling at least one vehicle function of an ego vehicle (10) on the basis of at least one optical notification signal (50, 52), in particular a warning signal, with regard to a traffic situation in a vehicle environment (L1 - L3) of the ego vehicle (10), in particular with regard to a potential hazard situation, wherein the optical notification signal (50, 52) is output by an optical output device (48) on an output surface in a vehicle environment (B1, B2) detected by at least one sensor device (12) for detecting the vehicle environment (L1 - L3) of the ego vehicle (10), in particular as a spatially resolved representation, comprising: - Receiving environmental data, in particular spatially resolved data, determined by at least one sensor device (12) with regard to the detected vehicle environment (B1, B2); - Determining at least one environmental geometry parameter in relation to the output surface based on the determined environmental data, wherein a 3D model for at least one section of the vehicle environment is determined based on the determined environmental data and the environmental geometry parameter is determined based on the 3D model; - Processing data characteristic of the environment data by means of an evaluation device (18) and thereby determining at least one notification parameter which is characteristic of the optical notification signal, in particular of a meaning of the optical notification signal in relation to the traffic situation; - Providing a message evaluation signal to control the vehicle function depending on at least one notification parameter. [2] Method according to claim 1, characterized by, that at least one environmental geometry parameter is a spatial position of the ego vehicle (10) in relation to the vehicle environment and / or a relative position of the ego vehicle (10) to the output surface. [3] Method according to any of the preceding claims, characterized by , that at least one of the environmental geometry dimensions is a topographic dimension of the output surface, which is in particular selected from a group of topographic dimensions which is characteristic of unevenness, curvature, irregularity, a slope, a surface structure, a surface roughness or a surface property, in particular a surface finish, combinations thereof or the like. [4] Method according to any of the preceding claims, characterized by that the 3D model includes the output area. [5] Method according to any of the preceding claims, characterized bythat the 3D model is determined based on environmental data using at least one 3D model generation device selected from a group comprising a LIDAR sensor, a stereo camera system, a pattern projection system with 3D image processing, a system for using a structure-from-motion method, a TOF camera and the like, as well as combinations thereof. [6] Method according to any of the preceding claims, characterized by , that monocular depth information is determined based on the spatially resolved environmental data and the 3D model is determined based on this. [7] Method according to any of the preceding claims, characterized by, that the optical output device (48) is an optical output device (48), in particular a projection module and / or a display device, of another vehicle (40) from the vehicle environment (L1 - L3) of the Ego vehicle (10), which is suitable and intended for outputting the notification signal into the vehicle environment (L1 - L3). [8] Notification system (1) for an ego vehicle (10) for automatically controlling at least one vehicle function of an ego vehicle (10) on the basis of at least one optical notification signal (50, 52), in particular a warning signal, with regard to a traffic situation in a vehicle environment (L1 - L3) of the ego vehicle (10), in particular with regard to a potential hazard situation, wherein the optical notification signal (50, 52) is output and / or outputtable by an optical output device (48) on an output surface in a vehicle environment (B1, B2) detected by at least one sensor device (12) for detecting the vehicle environment (L1 - L3) of the ego vehicle (10), in particular as a spatially resolved representation, wherein the notification system (1) is suitable and intended to receive environment data determined by the sensor device (12) with regard to the detected vehicle environment (B1, B2), in particular spatially resolved environment data, characterized bythat the notification system (1) is suitable and intended to determine at least one environmental geometry parameter in relation to the output surface based on the determined environmental data, and to determine a 3D model for at least one section of the vehicle's environment based on the determined environmental data, and to determine the environmental geometry parameter based on the 3D model, and to process characteristic data for the environmental data by means of an evaluation device (18), wherein thereby and depending on the environmental geometry parameter, at least one notification parameter can be determined and / or is determined which is characteristic for the optical notification signal, in particular for a meaning of the optical notification signal in relation to the traffic situation, wherein the notification system (1) is suitable and intended toto provide a message evaluation signal for controlling the vehicle function depending on at least one notification parameter. [9] Vehicle (10), in particular motor vehicle, comprising a notification system (1) according to the preceding claim.

Images