DE102017201728A1 - Control device for generating control data for actuators for configuring an interior situation of a motor vehicle and motor vehicle and method for operating a control device - Google Patents

Abstract

The invention relates to a control device (12) for generating control data (15) for actuators (16) for an interior of a motor vehicle (10). A hardware interface (21) receives sensor data (22) from sensors (14), generates input data (23) from the sensor data (22), and provides the input data (23) for polling by sensor-unspecific polling functions. A model plane (25) operates a plurality of models (28), each of the models (28) describing a respective object by attribute values (29) and being adapted to at least one of the attribute values (29) by means of a respective one of the retrieval functions based on the input data (23). An interpretation level (26) performs a plurality of interpretation functions (30), each interpretation function (30) determining a property (31) of at least one of the modeled objects based on at least one attribute value (29) of the models (28). A function level (27) operates control functions (32), wherein each control function (32) generates some of the control data (15) as a function of at least one attribute value (29) and / or in dependence on a determined property (31).

Description

The invention relates to a control device for generating control data for actuators, with which one can configure or influence an interior situation of a motor vehicle. The invention also includes a motor vehicle with the control device. Also belongs to the invention, a method for operating the control device in the motor vehicle.

For the detection of the situation in an interior of a motor vehicle, ie the passenger compartment, a separate control unit with its own, specific sensors is usually used for each individual application, which is then highly optimized for the application, but in the case of two applications, If similar sensors are required, the double sensors are also available. Examples of specialized sensors are seat-covering mats for the airbag control, ultrasonic sensors of the anti-theft alarm system, capacitive sensors in the steering wheel or a single optical sensor for driver monitoring during piloted driving. The separately provided control units, these sensors can not be used for other control functions or achieve synergy by combining the sensor data.

The use of multiple sensors, however, has advantages. From the DE 10 2014 219 326 A1 For example, a sensor fusion with a smartphone in the motor vehicle is known.

From the DE 10 2013 224 917 A1 For example, a method is known for detecting a size of attention describing a driver's attention. A control device receives measurement data as well as a steering angle from the steering wheel and an accelerator pedal angle from the accelerator pedal. The controller then monitors the driver. Another function is this control device but not intended.

From the DE 103 46 846 A1 a data processing unit for an installation device of a motor vehicle is known. This unit is able to merge road network data with information from environmental information sources.

The invention has for its object to use multiple times for the control of actuators of an interior of a motor vehicle resources of the motor vehicle.

The object is solved by the subject matters of the independent claims. Advantageous developments of the invention are disclosed by the dependent claims, the following description and the figure.

The invention provides a control device for generating control data for actuators for configuring an interior situation of a motor vehicle. A respective example of such an actuator is: a seat motor, a window motor, a respective mirror motor for a rearview mirror and / or side mirrors, a blower of an air conditioner, a heater and / or cooling device of an air conditioner, a steering wheel adjusting device, a media player (eg an MP3 player). player).

The control device is characterized by a modular design. A hardware interface is configured to receive sensor data from sensors of the motor vehicle by means of a respective sensor-specific driver and to generate input data from the received sensor data and to provide the input data for retrieval by sensory-unspecific polling functions. By means of a respective polling function, in each case at least a part of the input data can thus be queried or read out at the hardware interface, without having to know control of the sensors in order to get to those sensor data which are based on the respective input data. This is done by the hardware interface. The polling function thus represents a uniform protocol for retrieving input data, which remains unchanged even when an exchange of sensors. A sensor-specific signal processing of the sensor data is performed by the drivers, which can be adapted to the exchanged sensors. The hardware interface may also include the electrical connections for the sensors.

A model level is arranged to operate multiple models, each of the models describing a respective interior related object by attribute values. To adapt to the interior situation, each object is arranged to set at least one of the attribute values by means of one of the polling functions based on at least a part of the input data. In other words, each object can be represented by a model. In order to adapt the model to the object, the input data can be used, for which purpose the model requires no adaptation to the sensor in the manner described, since the input data can be polled sensor-nonspecifically or sensor-independently by means of the polling functions. For example, it is independent of a protocol that specifies the manufacturer of the sensor for receiving the sensor data. For example, a temperature value can be retrieved by means of a polling function, without that it must be known how to read the temperature value from the connected temperature sensor.

Based on the input data, not every model needs to be fully customizable, i. Not every attribute value needs to be set based on the sensor data alone. An interpretation level is configured to perform a plurality of interpretation functions, each interpretation function configured to each determine a property of at least one of the modeled objects based on at least one set attribute value (of at least one of the models). Each interpretation function thus interprets the situation in the interior based on the models. In this case, a property of the at least one modeled object can be detected. If, for example, the position of the upper body of the driver is sought while the driver is tilting out of the detection range of a camera (and thus is no longer recognizable in the camera image), then, for example, in the event that the object "glove box" based on the sensor data his Attribute value "Position" changed to "open" (the glovebox was opened), recognized by an interpretation function "driver position", that the driver obviously must have leaned towards the glove box.

With the model level and the interpretation level, a description of the situation in the interior is available, which can be created without knowledge of the control of the sensors, so sensoragnostisch, since the control of the sensors, i. reading the sensor data through the hardware interface. Likewise, the situation in the interior is determined regardless of what the situation is to be observed. So there is still no dependence on a control function provided. Thus, the situation in the interior is also provided functionally diagnostic.

Any control functions can now use this description of the interior. For this purpose, a function level is set up to operate control functions, wherein each control function is in each case set up for some of the control data for at least one of the actuators of the motor vehicle as a function of at least one set attribute value of at least one of the models and / or in dependence on at least one determined property of the at least one modeled object. The control functions thus access the models and / or the properties determined by the interpretation level in order to control the actuators for configuring the interior situation.

A network interface is finally adapted to send the control data via a data network of the motor vehicle to the actuators. Such a data network may, for example, be based on an Ethernet network and / or a CAN (Controller Area Network) bus and / or LIN (Local-Interconnect Network) bus and / or a FlexRay bus and / or or a MOST bus (MOST - Media Oriented System Transport).

The invention provides the advantage that a central architecture for the sensing of the interior function is provided, which is highly modular able to provide sensor and function diagnostically a uniform, global model of the interior and this a variety of comfort and safety functions available to deliver.

The invention also includes developments, the characteristics of which provide additional advantages.

The hardware interface is preferably set up to generate the said input data by aggregation and / or fusion and / or plausibility of the received sensor data. Aggregating results in the advantage that sensor data are combined, so that the hardware interface can already collect sensor data from different sensors and / or at different times, and thus no corresponding administration effort is necessary in the models. A merger has the advantage of combining sensor data from different sensors to thereby link information sources in the form of the multiple sensors, whereby the input data represent a more precise and / or more detailed measurement than the sensor data taken alone. A plausibility check has the advantage that measurement errors are already detected in the hardware interface and can be compensated or eliminated there in order to avoid an influence of a measurement error on one of the models.

In the model plane, at least one of the following objects is represented by one of each of the models: a vehicle occupant, the motor vehicle, an object arranged in the interior. A model for a vehicle occupant has the advantage that the effect of the actuator control on the vehicle occupant is represented or recognizable by the occupant model. In addition, non-measurable properties of the vehicle occupant can be derived by means of the model. The vehicle state can be represented by the model of the motor vehicle in order thereby to determine the boundary conditions that are currently present in the interior. to represent for the control functions, eg a viewing angle, from which one can see an outside mirror. An object model of an object arranged in the interior has the advantage that the position of the object in the interior and / or the influence of the object on the interior situation is represented. For example, a backpack stored in front of an airbag can be modeled as an object and the airbag can be switched off by a control function, depending on the size and / or the weight and / or the position of the backpack.

In order to advantageously describe an object for the control functions by means of a model, the following is particularly preferably provided. By a respective attribute value of the model of the vehicle occupant, for example, at least one of the following attributes is described: a 2D / 3D avatar representation (two-dimensional or three-dimensional model of the vehicle occupant), a position, an orientation, a mass (body weight), a pulse rate, a Respiratory rate, a song beat frequency, a lip movement (eg, movement frequency), a temperature, a skin moisture. By means of the attribute value of the position of the vehicle occupant, for example, a control function for the seat occupancy can be operated. An attribute value of a pulse rate can be used, for example, for an interpretation function for detecting the stress level. An attribute value of a respiratory rate can be used, for example, for an interpretation function for the recognition of a state of health (shortness of breath). An attribute value of a mass of the vehicle occupant can be used, for example, for a control function of a belt tensioner. An attribute value of a song beat frequency can be used by an interpretation function for a vigilance measurement of the vehicle occupant. An attribute value of a temperature, such as a skin temperature, is usable for a control function of an air conditioner. An avatar representation may comprise a plurality of attribute values and has the advantage that the respective spatial position of at least one limb can be detected or determined by means of the modeled limbs, even if these limbs are outside the detection range of the sensors of the motor vehicle.

With regard to the model of the motor vehicle (vehicle state model), for example, a respective attribute value of the model of the motor vehicle describes at least one of the following attributes: a mirror position, a seat position, a belt status, a vehicle speed, a terminal state of a voltage supply, a steering angle, a door state, a flap condition (for example, a trunk flap). An attribute value of a mirror position can be used to predict a movement of a head of the driver when he has to watch the traffic behind. An attribute value of a sitting position can be used to decide which controls in the interior of a given vehicle occupants can be reached by hand and which, however, must be able to be operated, for example, by voice control or viewing direction recognition. For example, an attribute value of a vehicle speed may be used to predict a lateral force when cornering. A clamp state of a power supply can be used to predict an available engine power of at least one actuator. An attribute value of a steering angle has the advantage that an internal state of the driver can be deduced based on a time profile of the changing attribute value. An attribute value of a door state has the advantage that, depending on an open position and / or closed position of the door, inflation of at least one actuator is possible. For example, an attribute value of a flap state may be used to control a "trunk open" indication.

With respect to an object model, for example, at least one of the following attributes is described by a respective attribute value of the model of the object: a position, a class, an orientation. An attribute value of a position can be used in the manner already described, for example for controlling an airbag. An attribute value of the class may indicate whether the object is a handbag or a digital camera or a smartphone, for example. An attribute becomes an orientation can be used, for example, to detect an orientation of a detection range of a camera of a smartphone, whereby the camera can be used as a vehicle-external sensor.

It is preferably provided that in the interpretation level at least one of the following properties is determined by one of the interpretation functions: a segmented 2D / 3D avatar representation, a NCAP classification (NCAP - New Car Assessment Program), a hand movement, a seat occupancy, a body pose, a degree of distraction, a degree of fatigue, an emotion, a stress level, a geometric identification, a line of sight, a head orientation, an age, a gender, a clothing class (eg "dressed warmly"). Each of these properties can now be determined on the basis of the total available attribute values of the models, without having to implement the control of the sensors in each of the interpretation functions. Instead, the situation in the interior, traced by the models, can be used as the basis for recognizing the respective property.

It is preferably provided that in the interpretation level by at least one of the interpretation functions, a context evaluation is performed which determines based on an environment description of the motor vehicle, as the environment of the motor vehicle and / or what is recognizable from the environment of the interior for a vehicle occupant. Thus, e.g. a respective position of at least one road user in the environment of the vehicle be described so that a respective reaction and / or attitude of the driver and / or another vehicle occupant can be placed in the situation context (eg "driver looks in the wing mirror to observe another motor vehicle ").

Said environment description may be received from an environment model based on environmental sensors such as environmental sensors. Radar, lidar, ultrasound, to name just a few examples, can be formed. Such an environmental model can be provided, for example, for piloted driving. Supplemented with navigation data and / or a digital road map, the immediate environment, i. e.g. Third-party vehicles, other road users such as pedestrians or cyclists, traffic signs, traffic lights, prominent points, be described by the environment model.

For various attributes of the interior situation there is a direct connection, such as the driver's line of sight, a braking intervention or an unexpected pulse increase.

The environment model can be located outside of the concept outlined here, ie also outside the control device, and only needs to be queried to evaluate the situation context of the interior situation, but not filled or synchronized or updated, like its own, internal model level.

The models need not be able to adjust all their attribute values based on the input data (processed sensor data). Therefore, it is preferably provided that at least one of the interpretation functions is set up to set at least one further attribute value in at least one of the models as a function of the property determined. Thus, by interpreting the situation imitated by the models in the interior, at least one further attribute value is derived or determined, for which in each case no sensor is required for detecting the respective attribute values.

At the functional level, at least one of the following controls is provided by each one of the control functions: gesture control, occupant notification, airbag control, driver dependent seat and / or cockpit fitting, lighting control, driver authentication, air conditioning control, 3D sound focusing, HRV biofeedback control (HRV - cardiac rhythm variability). The gesture control can advantageously fall back on the described avatar, for example, so that not every limb actually has to be detected by a camera. On the basis of a model of an object can even be additionally recognized in the gesture control, whether a vehicle occupant actually performs a control gesture or matured after the object. An occupant notification may, for example, perform a control of a display device and / or voice output device and / or a Haptikaktuators the motor vehicle to issue a message to a vehicle occupant. For example, the airbag controller may deactivate an airbag in the manner described if the associated or associated vehicle seat is occupied by an article. A driver-dependent seat and / or cockpit fitting may adapt the seating position and / or a design of graphical display elements depending on an identity of a person and / or physiological features of the person, for example their height and / or vision. For example, a lighting controller may direct an ambient light (indirect lighting) in the motor vehicle to control and / or a light spot for a reading vehicle occupant. In this case, for example, the occupant model for determining the viewing direction and / or head inclination of the vehicle occupant can be used to detect a reading activity, and a model of a book, which looks at the vehicle occupant, for aligning the light spot. Depending on an orientation of a visual field (viewing direction and / or head tilt), for example, a floor lighting for illuminating a footwell can be activated. A driver authentication test may use geometric features from an occupant model. For example, an air conditioning controller may control seat air conditioning and / or zone air conditioning (different temperatures and / or aeration levels for different room areas). In the motor vehicle, for example, the feedback control can adapt air conditioning and / or lighting to an internal state of a vehicle occupant signaled by the heart rhythm.

In order to operate the model level, the interpretation level and the function level, preferably a computing device is provided which is set up for this purpose. A respective model, a respective interpretation function and a respective control function may in each case be designed as a program module that can be executed by the computing device. Here is the Arithmetic device preferably additionally configured to subsequently install at least one new model and / or at least one new interpretation function and / or at least one new control function and to provide it with input data of the hardware interface and / or attribute values of other models. Thus, therefore, a new model and / or a new interpretation function and / or a new control function in the control device can be retrofitted. In this case, no adaptation to the existing sensors is necessary because a sensor-independent polling function can be used to retrieve the described input data from the hardware interface.

So far, only sensors have been described as external data sources. It is preferably provided that the network interface leading to the data network is set up to retrieve from the data network data from at least one vehicle external data source, for example an Internet server and / or a mobile terminal (for example a smartphone and / or Smartwatch and / or tablet PC) and to provide them at the model level and / or in the interpretation level and / or at the functional level. As a result, for example, a database and / or a sensor of a mobile terminal can be used for determining or providing at least one attribute value and / or at least one property and / or for generating control data.

The invention also includes a motor vehicle with sensors and actuators, which are coupled via an embodiment of the control device according to the invention. As a result, different control functions for controlling the actuators in the motor vehicle can be provided flexibly and exchangeably and retrofittably on the basis of sensor data. The motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a passenger car or truck.

The operation of the motor vehicle results in an embodiment of the method according to the invention for operating a control device in a motor vehicle. The hardware interface receives sensor data from sensors of the motor vehicle by means of a respective sensor-specific driver and generates input data from the received sensor data and makes the input data available for retrieval by sensor-unsupported polling functions. A model plane operates a plurality of models, each of the models describing a respective object related to an interior of the motor vehicle by attribute values and setting at least one of the attribute values by means of a respective polling function based on the input data. By "related" is meant that the object is inside or confined to the interior or seen from inside. An interpretation level performs at least one interpretation function, each interpretation function determining a property of at least one of the modeled objects based on at least one set attribute value of at least one of the models. A function level operates at least one control function, wherein each control function generates control data depending on at least one set attribute value of at least one of the models and / or in dependence on at least one determined property. A network interface sends the control data to at least one actuator of the motor vehicle.

The invention also includes developments of the method according to the invention, which have features as they have already been described in connection with the developments of the motor vehicle according to the invention. For this reason, the corresponding developments of the method according to the invention are not described again here.

In the following, embodiments of the invention are described. For this purpose, the single FIGURE (FIG.) Shows a schematic representation of an embodiment of the motor vehicle according to the invention.

The exemplary embodiments explained below are preferred embodiments of the invention. In the exemplary embodiments, the described components of the embodiments each represent individual features of the invention, which are to be considered independently of one another, which each further develop the invention independently of one another and thus also individually or in a different combination than the one shown as part of the invention. Furthermore, the described embodiments can also be supplemented by further features of the invention already described.

In the figure, functionally identical elements are each provided with the same reference numerals.

The figure shows a motor vehicle 10 , which may be, for example, a motor vehicle, especially a passenger car or truck. To be in a passenger compartment or interior 11 of the motor vehicle 10 In order to be able to influence the situation there, for example the air conditioning and / or arrangement of seats / mirrors and / or the presentation of media content, a control device can be used 12 be provided. The control device 12 can act as a single controller or as a composite of Be designed control units. In particular, the control device 11 a processor device 13 which may include one or more microprocessors and / or one or more microcontrollers. To the control device 12 can sensors 14 of the motor vehicle 10 be connected, for example, a 3-D camera and / or a 2-D camera and / or at least one temperature sensor and / or at least a microphone and / or at least one to wear on the body of the accessory for measuring body signals. For influencing the situation in the interior 11 can the control device 12 control data 15 for controlling actuators 16 of the motor vehicle 10 produce. Examples of an actuator 16 are each: a seat motor and / or a mirror motor and / or a power window motor and / or an infotainment system (information entertainment system), an air conditioner, a display device in an instrument cluster of the motor vehicle 10 , The control device 12 can with the actuators 16 over a data network 17 be coupled. The data network 17 can, for example, an Ethernet network 18 and / or a bus system 18 ', For example, a CAN bus include. To the data network 17 can the control device 12 over a network interface 19 be connected, eg a NIC (Network Connect Interface). Different network technologies can be accessed through a gateway 20 be coupled with each other.

By the processor device 13 Different program modules can be executed, individually or modularly in the control device 12 can be installed or implemented. It is provided that the program modules not to the existing sensors 14 have to be adjusted. Rather, it is a hardware interface 21 provided which sensor data 22 from the sensors 14 receive and from this input data 23 generated with a sensor-independent retrieval routine within the control device 12 can be retrieved. For controlling or sensor-specific retrieval of the sensor data 22 can be the hardware interface 21 a suitable driver for each sensor type 24 ie have driver software. The by means of the driver 24 Sensor data can be received by aggregation and / or fusion and / or plausibility check in the input data 23 being transformed.

Inside the control device 12 can in the computing device 13 a three level architecture, namely a model level 25 , an interpretation level 26 and a functional level 27 be provided. Every level 25 . 26 . 27 is formed by the fact that in each case similar program modules are summarized.

In the model level 25 can be used as program modules models 28 be provided. Every model 28 can be an object in the interior 11 or on the motor vehicle 10 represent. There may be an occupant model, a vehicle state model, and / or an object model. Every model 28 can describe the object described or represented by it by attribute values 29 only a few of which are provided with a reference numeral in the figure for the sake of clarity. At least some of the attribute values 29 can any model 28 set it to that from the hardware interface 21 at least part of an input data 23 retrieves. For this the model must 28 do not know how to get the associated sensor 14 controlled or read. Instead, a sensor-independent polling function can be used at the hardware interface 21 the required input data 29 request or read. By "sensor-independent polling function" is meant in particular a polling function, which is part of an API (Application Programming Interface) of the hardware interface 21 may be and / or a predetermined, sensor-independent protocol for reading the input data 23 provides. The polling function does not change even if at least one of the sensors 14 is exchanged. For example, a polling function can be provided for retrieving temperature values, by means of which input data with temperature values can be called up, regardless of which sensor 14 or sensor type the temperature values come from.

Interpretation levels may include interpretation functions 30 be provided. An interpretation function 30 can be at least one attribute value 29 read from one or more models and from it a property 31 an object of the motor vehicle 10 determine. This attribute 31 can then be described again as an attribute value or through multiple attribute values. These new attribute values can again be in the matching model 28 be stored.

The thus provided model-based description of the interior 11 can of different control functions 32 the functional level 27 be used. Each of the control functions 32 may be based on at least one respective attribute value 29 at least one model 28 and / or on the basis of at least one by a respective interpretation function 30 determined property 31 control data 15 generate, with which they at least one actuator 16 can control. So can for control functions 32 such as gesture control, airbag control, seat adaptation and / or cockpit adaptation, lighting control and / or other control functions 32 based on different sensors 14 by means of the models 28 and interpretation functions 30 the situation in the interior 11 described, so the control functions 32 the control data 15 to the current situation in the interior 11 can adjust. This can be the control functions 32 the sensors 14 over the model layer 25 and the interpretation layer 26 share. Also, a new control function can be added, which will then use the existing sensors 14 can use.

This allows the reduction of costs per control function through synergy in hardware and software 32 and thus the implementation of control functions 32 which otherwise would not be economical due to its own system costs, as would be required by the separate provision of sensors. Furthermore, an increase in robustness is possible, because through the mergers plausibility several sensors for each control function 32 can be used. Depending on the application and equipment feature allowed the control device 12 the complete substitution of other ECUs.

By increasing the detection potential of the control functions 32 and the fusion of sensor data 22 Moreover, there is also a redundancy given to the level of automated driving 3 to level 5 (Level - automation level) according to, for example, SAE J 3016 is provided.

The realization of the control device shown in the figure 12 has a model-level architecture 25 , Interpretation level 26 and functional level 27 on.

At the model level 25 Inmates and objects are classified and the vehicle condition is taken into account in a vehicle model. By means of fusion and aggregation of the sensor parameters the models become 28 with attribute values 29 busy. Sensor specific drivers 24 define the hardware interface 21 and the respective data types of the attribute values used for modeling.

At the interpretation level, the attribute values are processed into information describing the characteristics of the occupants and / or objects and / or the motor vehicle and which in turn are described as attribute values in the models 28 can be written back or synchronized.

At the function level control functions are running 32 independent of the sensor technology of the sensors 14 the models 28 serve. As output of the control functions 32 be over the data network 10 , for example via the gateway 20 , the control data 15 to the individual control units of the respective actuators 16 directed.

Overall, the examples show how a fusion of different sensors in the motor vehicle to a central situation model of the vehicle interior can be provided by the invention.

QUOTES INCLUDE IN THE DESCRIPTION

This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited patent literature

• DE 102014219326 A1 [0003]
• DE 102013224917 A1 [0004]
• DE 10346846 A1 [0005]

Claims (12)

Control device (12) for generating control data (15) for actuators (16) to configure an interior situation of a motor vehicle (10), wherein a hardware interface (21) is set up to receive sensor data (22) from sensors (14) of the motor vehicle (10) by means of a respective sensor-specific driver (24), to generate input data (23) from the received sensor data (22) and provide the input data (23) for polling by sensor-unspecific polling functions; a model plane (25) is arranged to operate a plurality of models (28), each of the models (28) describing a respective interior-related object by attribute values (29) and being adapted to at least one of the attribute values (28); 29) by means of one of the polling functions based on at least a part of the input data (23), - an interpretation level (26) is adapted to perform a plurality of interpretation functions (30), each interpretation function (30) each being adapted to a property (31) of at least one of the modeled objects on the basis of at least one set attribute value (29) at least one to determine the models (28) a function level (27) is set up to operate control functions (32), wherein each control function (32) is in each case adapted to control some of the control data (15) in dependence on at least one set attribute value (29) of at least one of the models (28 ) and / or in dependence on at least one determined property (31), and - A network interface (19) is adapted to transmit the control data (15) via a data network (17) of the motor vehicle (10) to the actuators (16). Control device (12) after Claim 1 wherein the hardware interface (21) is adapted to generate the input data (23) by an aggregation and / or fusion and / or plausibility check of the received sensor data (22). Control device (12) according to one of the preceding claims, wherein in the model plane (25) at least one of the following objects is represented by in each case one of the models (28): a vehicle occupant, the motor vehicle (10), an object arranged in the interior. Control device (12) after Claim 3 wherein at least one of the following attributes is described by a respective attribute value (29) of the model (28) of the vehicle occupant: a 2D / 3D avatar representation, a position, an orientation, a mass, a pulse rate, a respiratory rate, a song beat frequency , a lip movement, a temperature, a skin moisture; and / or by a respective attribute value (29) of the model (28) of the motor vehicle (10) at least one of the following attributes is described: a mirror position, a seat position, a belt status, a vehicle speed, a terminal state of a power supply, a steering angle, a door state a flap condition; and / or described by a respective attribute value (29) of the model (28) of the object of at least one of the following attributes: a position, a class, an orientation. Control device (12) according to one of the preceding claims, wherein in the interpretation level (26) at least one of the following properties (31) is determined by in each case one of the interpretation functions (30): a segmented 2D / 3D avatar representation, an NCAP classification, a hand movement, a seat occupancy, a body pose, a degree of distraction, a degree of fatigue, an emotion, a stress level, a biometric identification, a line of sight, a head orientation, an age, a gender, a clothing class. Control device (12) according to one of the preceding claims, wherein in the interpretation level (26) by at least one of the interpretation functions (30) a context evaluation is performed, which determines based on an environment description of the motor vehicle, such as the environment of the motor vehicle and / or what of the environment is recognizable from the interior for a vehicle occupant. Control device (12) according to any one of the preceding claims, wherein at least one of the interpretation functions (30) is adapted to set depending on the determined property (31) at least one further attribute value (29) in at least one of the models (28). Control device (12) according to one of the preceding claims, wherein in the functional level (27) at least one of the following controls is provided by in each case one of the control functions (32): a gesture control, an occupant notification, an airbag control, a driver-dependent seat and / or cockpit fitting, lighting control, driver authentication, air conditioning control, 3D sound focusing, cardiac rhythm variability biofeedback control. Control device (12) according to one of the preceding claims, wherein a computing device (13) is adapted to operate the model plane (25), the interpretation level (26) and the functional level (27) and in this case at least one new model and / or at least a new interpretation function and / or at least a new control function to install later and to provide with input data (23) of the hardware interface (21) and / or attribute values (29) of the models (28). Control device (28) according to one of the preceding claims, wherein the network interface (19) is adapted to receive from the data network (17) data at least one non-vehicle data source and in the model level (25) and / or in the interpretation level (26) and / or at the functional level (27). Motor vehicle (10) with sensors (14) and actuators (16) and a control device (12) according to one of the preceding claims. Method for operating a control device (12) in a motor vehicle (10), wherein a hardware interface (21) of sensors (14) of the motor vehicle (10) receives sensor data (22) by means of a respective sensor - specific driver (24), generates input data (23) from the received sensor data (22) and generates the input data (23) for provides a poll through sensor-unspecific polling functions, a model plane (25) operates a plurality of models (28), each of the models (28) describing a respective object related to an interior (11) of the motor vehicle (10) by attribute values (29) and at least one of the attribute values (29 ) by means of a respective polling function based on the input data (23), - an interpretation level (26) executes at least one interpretation function (30), each interpretation function (30) determining a property (31) of at least one of the modeled objects based on at least one set attribute value (29) of at least one of the models (28), - a function level (27) at least one control function (32) operates, each control function (32) each control data (15) in response to at least one set attribute value (29) at least one of the models (28) and / or in dependence on at least one generated property (31) generated, and - A network interface (19) the control data (15) to at least one actuator (16) for configuring an interior situation of a motor vehicle (10) emits.

Images