Methods for displaying information on a human-machine interface of a motor vehicle, computer program products, human-machine interfaces, and motor vehicles

Abstract

A method is described for a human-machine interface (4) for controlling a motor vehicle (2), wherein the human-machine interface (4) has at least one display device (8, 10, 12) for displaying information (34, 36, 38, 40, 42, 44), wherein at least one driving condition parameter is obtained, the driving condition parameter characterizing the driving condition of the motor vehicle (2), and wherein a load parameter characterizing the cognitive load of the driver (6) of the motor vehicle (2) is determined by means of an algorithm (20) based on the obtained driving condition parameter, thereby adapting the information density of the information to be displayed by means of the at least one display device (8, 10, 12) according to the load parameter, wherein the algorithm (20) includes a dataset having driving condition parameters, wherein a load parameter is assigned to each driving condition parameter, wherein the load parameter is based on at least one measured measurement parameter characterizing the driver's behavior. A computer program product, a human-machine interface, and a motor vehicle are also described.

Description

TECHNICAL FIELD

[0001] A method for displaying information on a human-machine interface of a motor vehicle, a computer program product, a human-machine interface and a motor vehicle are described herein. BACKGROUND

[0002] Methods, computer program products, human-machine interfaces and motor vehicles of the type mentioned in the opening paragraph for displaying information on a human-machine interface of a motor vehicle are known in the prior art.

[0003] The amount of information that a driver can highlight and quickly grasp depends on the cognitive load that the driver experiences in the current driving situation. Cognitive load reflects how much mental stress a driver experiences to fully understand the situation, in particular the driving situation, and to be able to react correctly. The more information a driver has to receive, the higher the cognitive load. The more complex the driving situation, the more the driver needs to concentrate. On simple routes with little traffic, less needs to be paid attention to than on busy, winding, high-speed routes. It is also important to avoid cognitive underload of the driver. On straight roads with little traffic and constant speed, the driver can lose concentration. In the first case, the driver can easily grasp and analyze a large amount of information from the human-machine interface. In the second case, the driver can be overwhelmed by too much information and no longer pay sufficient attention to the traffic situation. In the third, alert situation, the driver finds it more difficult to receive and fully process continuously changing and increasing information.

[0004] The driving situation describes the interaction between the driver, the vehicle and the environment.

[0005] Adaptive displays are known per se. In the simplest form, it is known to use different display modes during the day and at night, for example a night mode on the display. It is known that the color of the display can also be changed. Furthermore, it is known to configure the display according to the driving mode, for example in a sports car, the highway mode and the race track mode are different. In addition, there are a wide variety of displays in which information can be displayed in different sizes. The corresponding adaptation of the display is carried out automatically, for example depending on the ambient light, or manually, for example when selecting the display mode or the display color.

[0006] DE 10 2007 058 437 A1 discloses a method for communicating information to a driver of a motor vehicle, wherein a visual information display is displayed to the driver by means of a head-up display, the overall display of which comprises a set of adjacent display areas in which information displays can be displayed, each element of a set of possible information displays being assigned to a display area in which it is displayed. Therein, a characteristic driving situation parameter is determined which characterizes the current driving situation, wherein for each display area the information displays assigned to it are prioritized in accordance with the characteristic driving situation parameter, and wherein the content of each display area is determined in accordance with the prioritization made for it.

[0007] While the driving situation parameters known from the prior art can sometimes coincidentally be relevant to the cognitive load of the driver, there are also situations in which a large amount of information is to be displayed despite a high cognitive load of the driver. In these situations, the amount of information displayed can overwhelm the driver. SUMMARY

[0008] It is therefore the task of the present application to develop a method for displaying information on a human-machine interface of a motor vehicle, a computer program product, a human-machine interface and a motor vehicle of the aforementioned type, which makes it possible to determine the cognitive load of the driver more directly, and thus more precisely, and which makes it possible to configure the human-machine interface accordingly. Another task is to be able to take into account the individual cognitive performance of a specific driver.

[0009] This task is solved by a method for controlling a human-machine interface of a motor vehicle according to the present application, a computer program product according to the present application, a human-machine interface according to the present application and a motor vehicle according to the present application.

[0010] The following describes a method for controlling a human-machine interface of a motor vehicle, wherein the human-machine interface has at least one display device for displaying information, wherein at least one driving situation parameter is ascertained, which characterizes the driving situation of the motor vehicle, and wherein a load parameter is determined by means of an algorithm from the ascertained driving situation parameter, which characterizes the cognitive load of the driver of the motor vehicle, in order to adapt the information density of the information to be displayed by means of the display device of the at least one display device in accordance with the load parameter, wherein the algorithm comprises a data set with driving situation parameters, wherein each driving situation parameter is assigned a load parameter respectively, wherein the load parameter is based on at least one measured measurement variable which characterizes the behavior of the driver.

[0011] By determining the cognitive load of the driver and selecting a corresponding information density, it is possible to ensure that only information is displayed to the driver that he can actually process. This prevents the driver's information processing capacity from being influenced by too much and constantly changing information, leaving the driver with more mental resources to process traffic situations.

[0012] Here, the most relevant information can be selected according to the situation, for example, navigation information if the driver is approaching a road junction, speed information if the driver is driving too fast or too slow, or warnings if the traffic requires increased attention.

[0013] In a first extension, it can be provided that a behavior parameter characterizing the current behavior of the driver is also determined, wherein the information density to be displayed on the display device is varied in consideration of the determined behavior parameter.

[0014] The behavior of the driver is a reliable measure of the cognitive load of the driver. Thereby, the information density can be better matched to the current needs of the driver.

[0015] In a further extension, it can be provided that, for the calculation of the driving situation parameter, a prediction of the cognitive load of the driver at a predetermined time, over a predetermined period of time and / or at a predetermined distance is included.

[0016] Thereby, it is possible to predict the cognitive load in the short term and to select a suitable display configuration early in accordance with the expected cognitive load. Thus, the displayed information can already be selected to be the most important information before a situation requiring attention occurs.

[0017] In a further extension, it can be provided that a measure related to the driver is detected during normal driving operation of the motor vehicle and the driver is classified into one of a plurality of user type categories, wherein the information density is adapted in accordance with the user type category of the driver.

[0018] It is known that different drivers have different cognitive abilities in relation to various aspects and are stressed to different degrees in different driving situations. A novice driver therefore requires more attention and thus more cognitive outlay than an experienced driver. There are also differences between different drivers in terms of their ability to receive and process information, for example in relation to age. Furthermore, it is known that the driving time has an influence on the degree of concentration of the driver. Such measures can be detected within the scope of the present configuration, whereby a display configuration suitable for the driver can be selected.

[0019] This architecture can be used to provide different sets of information for different types of drivers. Some drivers can process a larger amount of information than others, thus preventing those who cannot process as much information from being overloaded by the human-machine interface.

[0020] In another extended configuration, the input parameters related to driving conditions can be configured to include measurements of the driver, the vehicle, and / or the environment.

[0021] Environmental measurement parameters may include road guidance, traffic, weather, daytime, etc.; driver-related measurement parameters may include human-machine interface interaction, line of sight direction, driving behavior, etc.; motor vehicle-related measurement parameters may include dynamics, use of auxiliary systems, etc.

[0022] These parameters have been shown to be suitable for predicting driver cognitive load. The faster a driver drives, the more attention they need to pay to road conditions. The more curved the road, the more steering input is required, which places a cognitive burden on the driver. The more road users there are, the more attention is required, as the driver must observe the behavior of other road users and react as necessary. For example, if a vehicle in front of the driver brakes, the driver must also brake. Monotonous driving environments—such as routes without curves and with few road users—reduce the driver's attention and concentration. In this situation, the driver's reaction behavior is affected.

[0023] In another extended configuration, at least two display configurations with different information densities can be set, wherein the information density is adapted by selecting the display configuration.

[0024] Two or more different display configurations can be set up, and these configurations may differ in more than one parameter dimension in some configurations. Therefore, different display configurations can display different amounts of information, display some information at different sizes, and change the position of the information. It should be noted that drivers often assume that information is located in a specific position, such as speedometer, RPM, travel length, etc. Therefore, a configuration could be considered where the information is selected and displayed in the center at the appropriate size. Other information can be placed in specific areas set up for that information.

[0025] In another extended configuration, the human-machine interface can have at least two display devices on which multiple pieces of information related to the driver of the motor vehicle can be displayed, wherein an algorithm is used to determine which information is displayed on which display device.

[0026] The corresponding display devices could be, for example, a central information display, a cockpit display, and / or a head-up display. In this way, very important information can be displayed, for example, on a display device close to the driver's field of vision—such as on a head-up display.

[0027] In another extended configuration, the algorithm can be trained using machine learning methods by having multiple test drivers perform test drives. During these test drives, characterization parameters describing driving conditions are detected and stored. The test drivers receive input requests to the input elements of the human-machine interface during the test drives, and the duration of the inputs, the input error rate, and / or the number of operation steps are detected and correlated with the characterization parameters by the algorithm.

[0028] Machine learning methods enable reliable assessment of highly complex situations and, in particular, prediction of future cognitive load based on different driving conditions. Such predictions are difficult to make using algorithms with classic configurations. Furthermore, this type of algorithm can continuously improve during ongoing operation, thus continuously improving the prediction of cognitive load and the ability to classify drivers into different user type categories based on their characteristics.

[0029] This algorithm can be used in the form of artificial intelligence, which is a complex filter that can be scaled up as previously discussed.

[0030] In another extended configuration, additional characterization parameters for the cognitive load of the test driver can be detected and correlated with characterization parameters of the driving condition during test driving. These characterization parameters may include vehicle position in the lane, number of lane departures, duration of lane departures, deviation from the expected speed, head movement, arm movement, steering wheel input, pedal input, and / or driver's line of sight.

[0031] Reaction time to complex tasks is a useful measure for determining a driver's cognitive load under specific conditions. Under current driving conditions, the more attention a driver needs to devote to the driving task, the longer it takes to complete the task. Driving precision—how precisely a driver stays within their lane, the frequency with which they cross lanes, and the duration of their lane departures—is an indicator of the level of cognitive load the driver is currently experiencing.

[0032] For example, monitoring of the driver using an internal camera allows for conclusions about the driver's current state. Rapid changes in gaze and steady input through the pedals and steering wheel can indicate high visual-manual load, while drivers without heavy load tend to exhibit balanced gaze and steady behavior. Furthermore, frequent pedal movements or steering wheel inputs may indicate high cognitive load.

[0033] Using multiple different test drivers also makes it possible to better differentiate between different user types.

[0034] The first independent subject relates to a human-machine interface (HMI) device for controlling a motor vehicle, wherein the HMI has at least one display device for displaying information, wherein means are provided for obtaining at least one driving condition parameter describing the driving condition of the motor vehicle, and wherein means are provided for determining a load parameter based on the obtained driving condition parameter using an algorithm, wherein the load parameter characterizes the cognitive load of the motor vehicle driver, and wherein means are provided for adapting the information density of the at least one display device, the information density being the information density of information to be displayed on the display device based on the load parameter, wherein the algorithm includes a dataset having driving condition parameters, wherein a driving condition parameter is assigned to each load parameter, wherein the load parameter is based on at least one measurement parameter characterizing the driver's behavior.

[0035] In the first extended configuration, a means for obtaining at least one behavioral parameter, wherein the behavioral parameter characterizes the driver's current behavior, and wherein the means for adapting the information density is configured to change the information density to be displayed on the display device in consideration of the obtained behavioral parameter.

[0036] In another extended configuration, a predictive device may be provided for calculating the cognitive load of the driver at a predetermined time, within a predetermined time period, and / or at a predetermined distance.

[0037] In another extended configuration, sensors for detecting driver-related measurement parameters in normal driving mode of the motor vehicle and a classification device for classifying the driver into one of several categories are provided, wherein the device is configured to perform display configuration based on the driver's user type category.

[0038] In another extended configuration, input parameters related to driving conditions can be set to include parameters about the driver, vehicle, environment, vehicle dynamics, road guidance, traffic conditions, and / or weather.

[0039] In another extended configuration, at least two display configurations with different information densities can be provided, wherein the means for adapting the information density is configured to adapt the information density by selecting the display configuration.

[0040] In another extended configuration, the human-machine interface can be configured to have at least two display devices, on which multiple pieces of information related to the motor vehicle driver can be displayed respectively, wherein an algorithm is configured to determine which information to display on which display device.

[0041] In another extended configuration, the algorithm can be trained using machine learning methods by having multiple test drivers perform test drives. During these test drives, characterization parameters are detected using a detection device and stored in memory to describe the driving conditions. The test drivers receive input requests to the input elements of the human-machine interface during the test drives, and the duration of the inputs used to perform the inputs is detected using a clock and correlated with the characterization parameters using an algorithm.

[0042] In another extended configuration, a detection device can be provided for detecting additional measurement parameters related to the cognitive load of the test driver, and a calculation device for relating these parameters to characterizing driving conditions during test driving. The characterizing measurement parameters include the vehicle's position in the lane, the number of times it crossed lanes, the duration of lane crossings, deviation from the expected speed, head movements, arm movements, steering wheel input, pedal input, and / or the driver's line of sight.

[0043] Another separate topic relates to a computer program product having a computer-readable storage medium on which instructions are embedded, the instructions causing, when executed by at least one computing unit, the at least one computing unit being configured to perform the above-described method for controlling a human-machine interface for a motor vehicle.

[0044] The method can be implemented in a distributed manner on one or more computing units, thereby executing specific method steps on one computing unit and other method steps on at least one other computing unit, wherein computational data can be transferred between computing units if necessary.

[0045] Another separate topic relates to a human-machine interface having at least one display device, at least one computing unit, and at least one storage medium connected to the computing unit, on which a computer program product of the type described above is stored, which can be executed by the computing unit.

[0046] When used in motor vehicles, the corresponding human-machine interface can have the features and advantages mentioned above.

[0047] Another independent topic relates to a human-machine interface for motor vehicles, having at least one display device for optically displaying information related to the motor vehicle driver, wherein at least one computing unit is provided, the computing unit being connected to at least one storage medium, wherein the computing unit is configured to control at least one display device, the storage medium storing at least two different display configurations for operating at least one display device, wherein the computing unit is connected to at least one driving condition sensor that detects measurement parameters related to driving conditions, wherein the computing unit is configured to obtain at least one driving condition parameter from the input parameters of the driving condition sensor using an algorithm, the driving condition parameter characterizing the driving condition of the motor vehicle, and determine a load parameter characterizing the cognitive load of the motor vehicle driver based on the obtained driving condition parameter, and select one of the display configurations based on the load parameter and display it using the at least one display device, wherein the algorithm includes a dataset of driving condition parameters, wherein a load parameter is assigned to each driving condition parameter, wherein the load parameter is based on at least one measured measurement parameter characterizing driver behavior.

[0048] The corresponding driving condition sensors may be, for example, cameras, radar systems, vehicle-to-vehicle communication devices, vehicle-to-environment communication devices, navigation systems and / or weather sensors, such as temperature and / or rain sensors.

[0049] The algorithm could be, for example, based on a family of characteristic curves.

[0050] In a further extended configuration, the computing unit may be connected to at least one driver monitoring sensor that detects driver-related measurement parameters, wherein the computing unit is configured to calculate load parameters using the measurement parameters from the driver monitoring sensor.

[0051] Corresponding driver monitoring sensors could be, for example, cameras that are pointed at the driver and detect the driver's head movements, gestures, and gaze parameters, such as eyelid closure time, gaze duration, gaze direction, and / or eye movements. Another driver monitoring sensor could be a simple eye sensor.

[0052] In another extended configuration, the computer unit can be configured to monitor the interaction between the driver and the human-machine interface and to detect measurement parameters describing that interaction.

[0053] This allows for the monitoring and addition of input actions, such as operation duration, operation errors, and operation interruptions, to the display configuration.

[0054] In another extended configuration, the computing unit can be connected to at least one vehicle sensor that detects measurement parameters related to the driving state of the motor vehicle.

[0055] Such sensors can be, for example, pedal sensors for detecting pedal input, steering wheel sensors for detecting steering input, speed sensors, acceleration sensors for detecting acceleration and / or turning speed, and / or thrust reversers (Schlupf sensors).

[0056] In another extended configuration, at least two display devices may be provided, wherein the computing unit is configured to select which of the at least two display devices to display driver-related information based on the calculated cognitive load.

[0057] Such display devices can be, for example, head-up displays, central information displays, and / or cockpit displays.

[0058] In another extended configuration, the algorithm stored on the storage medium can be configured to be a self-learning algorithm.

[0059] Self-learning algorithms can handle very complex situations.

[0060] Depending on the configuration, the algorithm can also possess artificial intelligence.

[0061] Another separate topic concerns a motor vehicle with a human-machine interface of the aforementioned type. Attached Figure Description

[0062] Other features and details derive from the following description, in which at least one embodiment is described in detail (with reference to the accompanying drawings where necessary). The described and / or graphically illustrated features form the subject matter individually or in any meaningful combination, and in particular, may also be the subject matter of one or more separate applications. Identical, similar, and / or functionally identical components are given the same reference numerals. This is schematically illustrated as follows:

[0063] Figure 1 Motor vehicles equipped with human-machine interfaces;

[0064] Figure 2A B: Under two different configurations Figure 1 Display devices for human-machine interfaces;

[0065] Figure 3 : Figure 1 The driving conditions of the motor vehicles in the vehicle;

[0066] Figure 4A B: Used for training Figure 1 A schematic diagram of the algorithm principle of the human-computer interface in China, and

[0067] Figure 5 : A schematic diagram of the decision-making architecture of this human-computer interface. Detailed Implementation

[0068] Figure 1 The vehicle 2 is shown with human-machine interface 4 (the component outlined in dashed lines).

[0069] Human-machine interface 4 is the interface between motor vehicle 2 and driver 6, and, when necessary, with other passengers. Through human-machine interface 4, driver 6 can receive information from motor vehicle 2 and information about motor vehicle 2, and can make control inputs to motor vehicle 4 via suitable input devices (not shown), such as for navigation, multimedia control, air conditioning, lighting, etc.

[0070] The human-machine interface 4 has three displays: a head-up display 8, a cockpit display 10, and a central information display 12. The head-up display 8 displays information on the windshield of the vehicle 2, the cockpit display 10 is positioned directly in front of the driver 6 (not shown) in front of the steering wheel, and the central information display 12 is positioned... Figure 1 (Not shown in the image) Near the center of the dashboard.

[0071] The human-machine interface 4 has a control device 14, which has a computing unit 16 and a storage medium 18, on which an algorithm 20 is stored. The algorithm will be described in detail below.

[0072] Control device 14 is connected to multiple sensors, among which, in Figure 1 The example shown includes radar sensor 22, steering angle sensor 24, traffic camera 26, and driver monitoring camera 28. Control device 14 can be connected to a number of additional sensors.

[0073] In addition to radar sensor 22 and traffic camera 26, the first group of such sensors can also include other sensors used for traffic monitoring, such as lidar, or communication devices, such as vehicle-to-vehicle communication devices or vehicle-to-infrastructure communication devices, navigation systems, weather sensors, etc., all of which are used to obtain information about traffic conditions.

[0074] In addition to the steering angle sensor 24, the second set of corresponding sensors can also be sensors used to monitor the condition of the vehicle, such as speed sensors, wheel speed sensors, drive sensors, pedal sensors, etc.

[0075] In addition to the driver monitoring camera 28, the fatigue sensor can also be used in the third group of driver monitoring sensors. However, the pedal sensor and steering angle sensor 24 mentioned in the second group can also be used for driver monitoring because the driver's actions on the control devices of the motor vehicle 2, such as the steering wheel, accelerator pedal or brake pedal, can be detected by the pedal sensor and steering angle sensor.

[0076] Radar sensor 22 and traffic camera 26 are used to monitor traffic conditions ahead of vehicle 2. With the help of this information, control device 14 can make predictions about current and future traffic conditions and situations using algorithm 20.

[0077] With the help of the steering angle sensor 24 and other sensors used to monitor the vehicle 2, the control device 14 can obtain information about the dynamic state of the vehicle 2.

[0078] The driver monitoring camera 28 can determine the current level of activity or distraction of the driver 6. For example, the driver monitoring camera 28 can detect the movement and direction of the driver 6's head 30 and / or eyes. In addition to monitoring the control inputs to the vehicle 2 via the steering wheel and pedals, this information also allows for conclusions about the cognitive load of the driver of the vehicle 2.

[0079] Figure 2A B shows two different display configurations, A and B. Figure 1 The human-machine interface 4 shown includes display devices 8, 10, and 12.

[0080] Display devices 8, 10, and 12 are located on instrument panel 32.

[0081] exist Figure 2A In the configuration shown, the head-up display 8 shows current driving speed information 34, navigation information 36, and lane keeping information 38, thus providing comprehensive notification to the driver.

[0082] The cockpit display 10 also shows the current driving speed information 34 and the engine speed information 40. In addition, it also displays multimedia information 42.

[0083] Map information 44 is displayed on the central information display 12.

[0084] Figure 2A A display configuration A is shown in which the driver has a low cognitive load and is able to receive and process a large amount of information from the human-machine interface 4.

[0085] On the contrary, according to Figure 2B In display configuration B, the cognitive load is higher, and it is displayed relative to the data provided. Figure 2A The amount of information displayed is very small for the purpose of this configuration.

[0086] Therefore, only navigation information 36 is displayed on the head-up display 8. Only driving speed information 34 is displayed on the cockpit display 10.

[0087] In addition to displaying map information 44, the central information display 12 also displays multimedia information 42.

[0088] Figure 2B The configuration shown allows the driver to quickly obtain the most relevant information in the corresponding driving situation.

[0089] Figure 3 Show Figure 1 The driving situation of motor vehicle 2 in the text.

[0090] Motor vehicle 2 is traveling toward road intersection 46. There is heavy traffic at road intersection 46. Another motor vehicle 48 is traveling in front of motor vehicle 2. Another motor vehicle 50 is approaching motor vehicle 2 from the opposite direction. Road intersection 46 is being crossed by another motor vehicle 52. Motor vehicle 54 traveling in the opposite direction is waiting. Pedestrian 56 is crossing zebra crossing 58.

[0091] At this point in time, the cognitive load of driver 6 in vehicle 2 increases only slightly as the driver prepares for navigation to the upcoming road intersection 46. The closer the driver gets to intersection 46, the higher the cognitive load becomes, as the driver must simultaneously monitor the behavior of numerous traffic participants 48 to 56 and perform navigation. In this situation, it is difficult for driver 6 to receive all the available information about navigation and vehicle 2; therefore, it makes sense to significantly reduce the amount of information displayed on human-machine interface 4 and to display the most important information in a correspondingly large and concise manner to immediately capture attention.

[0092] Figure 4A B shows the training... Figure 1 A schematic diagram of the principle of algorithm 20 in the human-computer interface 4.

[0093] Algorithm 20 has two distinct classification dimensions: one related to the current driving conditions and the other to the driver. Algorithm 20 is a self-learning algorithm developed by training test drivers on test drives.

[0094] During the training of Algorithm 20, representational parameters describing driving conditions are detected and analyzed using a data detector. Additionally, other measurements of driver distraction, such as eye or head movements and gaze direction, gestures and / or pedal and steering angle settings, can be recorded. Furthermore, the duration before the driver makes a steering input, the driver's position within the lane, the conditions under which the driver leaves the lane, how often and how frequently, and how consistently the speed is maintained can also be detected.

[0095] During the previously mentioned test drive, the test driver was repeatedly asked to perform one or more standardized inputs on the human-machine interface 4. Different traffic conditions existed during these inputs. The duration of input required by the test driver for the requested inputs was related to both the driver's cognitive load due to the driving conditions and the driver's distraction, such as distraction caused by the request for input information.

[0096] The measured operation time for completing the task, along with the characterization parameters, is recorded and analyzed.

[0097] Figure 4A This demonstrates how to categorize different drivers into different driver type categories based on previously described input parameters about the current situation (vehicle dynamics, route, traffic, weather, human-machine interface input).

[0098] Experienced drivers exhibit less lane departure under similar driving conditions and are able to input information more quickly through the human-machine interface 4 than less experienced drivers. The human-machine interface 4 should impose a less burden on the latter than on the former, for example, through simplified menu navigation. Such drivers are then classified into a lower driver type level than experienced drivers.

[0099] Figure 4B This demonstrates how to analyze a driver's cognitive load based on the same input parameters, such as current location, current road segment, traffic conditions, and weather.

[0100] Therefore, it is possible to pre-select problematic display configurations A and B on the one hand, and to correlate driving conditions and cognitive load on the other. This enables the development of an algorithm 20 for use in motor vehicle 2, which makes decisions based on information displayed on displays 8, 10, and 12 of the human-machine interface 4.

[0101] Figure 5 A schematic diagram of the decision-making architecture of human-machine interface 4 is shown.

[0102] In the subsequent driving operation, regarding the situation according to... Figure 4A The same input parameters are used for detection during the training of B and B, and the analysis and processing are carried out with the help of artificial intelligence algorithm 20.

[0103] In addition to the current input, a so-called digital electronic horizon is created, which is a prediction of driving conditions that will occur in the short term. This horizon can include, for example, a distance of 50 to 200 meters or 1000 meters, or a time period of, for example, 5 to 30 seconds. This digital electronic horizon allows for the dynamic prediction of corresponding input parameters (e.g., using ADASIS).

[0104] Algorithm 20 uses the input parameters to calculate, on the one hand, which driver type the current driver belongs to. On the other hand, Algorithm 20 predicts the cognitive load that will occur in the upcoming route segment. This information is transmitted to the control device 14 of the human-machine interface 4, which selects the corresponding display configurations A and B from it.

[0105] Based on user type, for example, three cognitive ability levels (3 high - 2 medium - 1 low) can be mapped to, for example, five display levels (4 highest - 3 high - 2 medium - 1 low - 0 lowest). For a driver with a cognitive ability level of 3 high, the load level 3-2-1 can be assigned to, for example, display level 4-3-2; for a driver with a cognitive ability level of 2, display level 3-2-1 can be assigned; and for a driver with a cognitive ability level of 1, display level 2-1-0 can be assigned.

[0106] In the alternative configuration, a family of characteristic curves can be created artificially, and the corresponding display configurations A and B can be selected according to the input parameters based on this family of characteristic curves.

[0107] Although the subject matter has been described and illustrated in detail by way of examples, the invention is not limited to the disclosed examples, and further variations can be derived by those skilled in the art. Thus, it is evident that numerous variations are possible. It is also apparent that the exemplary embodiments mentioned are merely illustrative and should in no way be construed as limiting the scope of protection, application possibilities, or configuration of the invention. Rather, the foregoing description and accompanying drawings enable those skilled in the art to embodied the described exemplary embodiments, wherein, with an understanding of the disclosed inventive concept, those skilled in the art can make various changes, for example, in the function or arrangement of the various elements mentioned in the exemplary embodiments, without departing from the scope of protection defined by the claims and their legal equivalents (e.g., further exposition in the specification).

[0108] Reference tag list

[0109] 2 Motor vehicles

[0110] 4. Human-Machine Interface

[0111] 6 drivers

[0112] 8. Head-up display

[0113] 10. Cockpit Displays

[0114] 12 Central Information Display

[0115] 14 Control device

[0116] 16 Computing Units

[0117] 18 Storage Media

[0118] 20 Algorithms

[0119] 22 Radar Sensors

[0120] 24 Steering Angle Sensor

[0121] 26 Traffic cameras

[0122] 28 Driver monitoring cameras

[0123] 30 heads

[0124] 32. Dashboard

[0125] 34 Driving speed information

[0126] 36 Navigation Information

[0127] 38 Lane Keeping Information

[0128] 40 RPM information

[0129] 42 Multimedia Information

[0130] 44 Map Information

[0131] 46. ​​Road intersection

[0132] Motor vehicles 48, 50, 52, 54

[0133] 56 pedestrians

[0134] 58 Zebra Crossing

[0135] A and B display configuration

Claims

1. A method for controlling a human-machine interface (4) of a motor vehicle (2), wherein, The human-machine interface (4) has at least one display device (8, 10, 12) for displaying information (34, 36, 38, 40, 42, 44), wherein at least one driving situation parameter is determined, which characterizes a driving situation of the motor vehicle (2), and wherein a load parameter is determined by means of an algorithm (20) from the determined driving situation parameter, which characterizes a cognitive load of a driver (6) of the motor vehicle (2), so that the information density of the information to be displayed by means of the display device (8, 10, 12) on the at least one display device (8, 10, 12) is adapted in accordance with the load parameter, wherein the algorithm (20) comprises a data set with driving situation parameters, wherein each driving situation parameter is assigned a load parameter, respectively, wherein the load parameter is based on at least one measured measured variable characterizing the driver behavior, characterized in that The algorithm (20) is trained by means of a machine learning method in such a way that a test drive is carried out by a plurality of test drivers, wherein driving situation characterizing parameters are detected and stored during the test drive, wherein the test drivers obtain input requirements for input elements of the human-machine interface during the test drive, wherein the input duration for carrying out the input, the input error rate and / or the number of operating steps are detected and correlated with the driving situation characterizing parameters by means of the algorithm (20).

2. The method of claim 1, wherein, A behavior parameter characterizing the current behavior of the driver is also determined, wherein the information density to be displayed on the display device (8, 10, 12) is varied in consideration of the determined behavior parameter.

3. The method of claim 1 or 2, wherein, For calculating the load parameter, a prediction of the cognitive load of the driver (6) at a predetermined time, over a predetermined period of time and / or at a predetermined distance is included.

4. The method of claim 1 or 2, wherein, Measured variables relating to the driver (6) are detected during normal driving operation of the motor vehicle (2) and the driver (6) is classified into one of a plurality of categories, wherein the information density is adapted in accordance with the user type category of the driver (6).

5. The method of claim 1 or 2, wherein, The input variables relating to the driving situation include environmental, driver (6) and / or motor vehicle (2) measured variables.

6. The method of claim 1 or 2, wherein, At least two display configurations (A, B) with different information densities are provided, wherein the information density is adapted by selecting a display configuration (A, B).

7. The method of claim 1 or 2, wherein, The human-machine interface (4) has at least two display devices (8, 10, 12) on which a plurality of information (34, 36, 38, 40, 42, 44) relating to the driver (6) of the motor vehicle (2) can be displayed, respectively, wherein it is determined by means of the algorithm (20) on which display device (8, 10, 12) which information (34, 36, 38, 40, 42, 44) is displayed.

8. The method of claim 1 or 2, wherein, Further representative measured variables for the cognitive load of the test driver (6) are detected during the test drive and correlated with the representative parameters of the driving situation, wherein the representative measured variables include vehicle position on the lane, number of lane departures, duration of lane departures, deviation from the desired speed, head movement, arm movement, steering wheel input, pedal input and / or gaze direction of the driver.

9. Computer program product with a computer-readable storage medium (18), in which instructions are embedded which, when executed by at least one computing unit (16), cause the at least one computing unit (16) to be set up to carry out the method according to any one of the preceding claims.

10. Human-machine interface (4) with at least one display device (8, 10, 12) and at least one computing unit (16) and at least one storage medium (18) connected to the computing unit (16), in which the computer program product according to claim 9 is stored, which can be executed by the computing unit (16).

11. A human-machine interface for a motor vehicle (2), having at least one display device for optically displaying information relating to a driver (6) of the motor vehicle (2), wherein At least one computing unit (16) is provided, which is connected to at least one storage medium (18), wherein the computing unit (16) is set up to control the at least one display device (8, 10, 12), wherein at least two different display configurations (A, B) for operating the at least one display device (8, 10, 12) are stored on the storage medium (18), wherein the computing unit (16) is connected to at least one driving situation sensor (22, 26), which detects at least one driving situation-related measured variable, wherein the computing unit (16) is set up to calculate at least one driving situation parameter from the input variables of the driving situation sensor (22, 26) by means of an algorithm (20), which represents the driving situation of the motor vehicle (2), and to determine a load parameter from the calculated driving situation parameter, which represents the cognitive load of the driver (6) of the motor vehicle (2), and to select one of the display configurations (A, B) and to display it by means of the at least one display device (8, 10, 12), wherein the algorithm (20) comprises a data set with driving situation parameters, wherein each driving situation parameter is assigned a load parameter, wherein the load parameter is based on at least one measured measured variable representing the driver's behavior, characterized in that The algorithm (20) has been trained by a machine learning method in such a way that a plurality of test drives have been performed by test drivers, wherein during the test drives characteristic parameters have been detected by means of detection means and stored in a memory for describing driving situations, wherein the test drivers during the test drives obtain input requirements for input elements of the human-machine interface by means of communication means, wherein input durations for performing the inputs are detected by means of a clock and correlated to the characteristic parameters by means of the algorithm (20).

12. The human-machine interface of claim 11, wherein, The computing unit (16) is connected to at least one driver monitoring sensor (28) which detects a measured variable relating to the driver (6), wherein the computing unit (16) is configured to calculate a load parameter using the measured variable of the driver monitoring sensor (28).

13. The human-machine interface of claim 12, wherein, The computing unit (16) is configured to monitor the interaction of the driver (6) with the human-machine interface (4) and to detect a measured variable describing the interaction.

14. Motor vehicle having a human-machine interface (4) according to any one of claims 10 to 13.

Images