Method for actuating at least two actuators of motor vehicle, motor vehicle, control unit for motor vehicle, and method for operating motor vehicle

Abstract

The invention relates to the actuation of actuators (12a, 12b, 12c, 12d) in a motor vehicle (1) by means of an artificial intelligence unit, in particular for providing an in-vehicle experience. When one actuator deviates from the target value, the target value for the other actuators is adjusted so that the in-vehicle experience continues to conform to the target setting.

Description

Technical Field

[0001] The present invention relates to a method for controlling at least two actuators of a motor vehicle, in particular for providing an in-vehicle experience. The present invention also relates to a motor vehicle and a controller in which the method according to the present invention can be executed, and the controller is configured for such a motor vehicle. The present invention also relates to a method for operating a motor vehicle, in particular for providing an in-vehicle experience. Background Art

[0002] When the vehicle occupants are not engaged in the driving task of the motor vehicle, an in-vehicle experience is provided for the vehicle occupants. This can occur during rest or during a journey in a self-driving motor vehicle without manual control intervention.

[0003] Typical in-vehicle experiences include providing a comfortable atmosphere by providing warm air, operating seat heating, lighting experiences (especially red light), soothing music, etc.

[0004] A motor vehicle with sensors is known from US2018 / 0134116 A1, and the sensors detect conditions existing inside and outside the motor vehicle. In order to provide optimal comfort for the vehicle occupants, complex determination of input data (phone, calendar, email) is required to give complex actuator control (delivering air in the motor vehicle, heating the passenger compartment, humidifying and dehumidifying, lighting, sound, seat position and seat heating). At this time, machine learning is used for such complex determination.

[0005] Furthermore, a method for detecting the position of a user by means of an artificial intelligence unit is known from US2021 / 0100480 A1, in which measurement values of multiple sensors are fed to the artificial intelligence unit.

[0006] When providing an in-vehicle experience or in other cases of jointly controlling multiple actuators of a motor vehicle, it is possible that the occupants have made changes to the settings themselves. For example, if an occupant pushes their seat forward, the warm air delivered to the rear seat may become too hot, and the lighting on the display may seem too bright, etc. Summary of the Invention

[0007] The object of the present invention is to make the actuator control in a motor vehicle more flexible.

[0008] This object is achieved by a method for controlling at least two actuators of a motor vehicle having the features of claim 1, a motor vehicle having the features of claim 8, a controller having the features of claim 9, and a method for operating a motor vehicle having the features of claim 10.

[0009] The method for controlling at least two actuators of a motor vehicle according to the present invention is carried out using an artificial intelligence unit. The aim of the method is in particular to provide an in-vehicle experience. For at least one predetermined actuator, a target setting / target state / target configuration is preset respectively, and this target setting is assigned to the target value of a predetermined input variable. When there is a deviation between the actual value and the target value of the predetermined input variable, the artificial intelligence unit changes the target setting for at least one predetermined actuator.

[0010] The desired flexibility is achieved by this method: the method only needs to be defined once, that is, by presetting the target setting for at least one predetermined actuator, but due to the use of the artificial intelligence unit, even if the actual value of the predetermined input variable is different from the target value, the desired effect (in-vehicle experience) can be achieved as much as possible.

[0011] According to a preferred embodiment, target settings are preset for at least two predetermined actuators. The target setting of one actuator defines the target value of a predetermined input variable, and when there is a deviation between the actual setting and the target setting of a predetermined actuator, the artificial intelligence unit changes the target setting for another predetermined actuator.

[0012] In the above example (where the vehicle occupant changes their seat position), the target seat position can define the target value of a predetermined input variable, and the artificial intelligence unit changes the target setting for at least another actuator accordingly, such as changing the target setting of the actuator for outputting optics and / or the actuator for outputting thermodynamics and / or the actuator for outputting acoustics.

[0013] Preferably, it is stipulated for this purpose that the user can control at least some of the predetermined actuators in such a way that these actuators deviate from the target setting. This is the case with the seat. The artificial intelligence unit then changes the target setting for another part of the predetermined actuators that are not controlled by the user.

[0014] For example, if the user does not want the warm air to be too hot and reduces the ventilation volume, in order to create a comfortable in-vehicle experience, the share of red light in the light can be increased (by controlling more red light-emitting diodes, etc.).

[0015] According to another preferred embodiment of the present invention, the predetermined input variable is a variable reflecting user preferences. This can directly affect the target setting of individual actuators, such as the target setting for a seat, the target setting for the volume of a device for outputting sound in a motor vehicle, the target setting for the brightness of a light, and so on. However, user preferences can also be described in a more complex way, for example, by a vector including multiple items, where, for example, each item in the vector is a target value for a different actuator. The predetermined input variable reflecting user preferences can furthermore simply be a characteristic parameter. In addition, the variable reflecting user preferences can be determined by means of a sensor device or an artificial intelligence unit: that is, the reaction of the user to a previous in-vehicle experience can be detected by a camera or the like and then evaluated by the artificial intelligence unit.

[0016] It is feasible that the predetermined input variable is represented numerically (for this purpose). That is, it is possible that the user generally desires the light to be brighter than the light preset through the in-vehicle experience. Alternatively or additionally, the predetermined input variable can also be a logical variable. For example, the user can select from multiple words ("warm", "comfortable", "active", "fun", etc.).

[0017] The binary input variable can also relate to situations other than providing an in-vehicle experience, such as driving a motor vehicle. As is well known, a vehicle driver can set whether they want to drive "sporty" or "economical" (fuel-saving).

[0018] According to another preferred embodiment, the target setting can be changed by the user at least partially, preferably completely. The difference between this embodiment and the situation where the user can actually deviate from the target setting is that in this embodiment, although the user can change the target setting as data / information, they do not have to actually deviate from the target setting. If the user deviates from the target setting, the artificial intelligence unit follows the changed target setting. In this way, the user can preset their own perceptual preferences for the in-vehicle experience.

[0019] According to another preferred embodiment, the pre-determined input variable is a variable detected by at least one sensor, where the sensor is not affected by the actuator. In the embodiments described above, the user can manipulate at least some of the pre-determined actuators to deviate from their target settings and detect the actual settings at this time. Differently, in the embodiments being discussed now, environmental influences can be detected. That is, for example, the brightness outside the motor vehicle (daytime, fog, night) can define the target value of the pre-determined input variable, and thus can also define the target setting for at least one pre-determined actuator. It is conceivable that this especially relates to the brightness that should be provided in the motor vehicle. For example, the starry sky detected by a camera serving as a sensor can also be displayed on the display / in the roof lining, so that the vehicle occupants feel as if they are outdoors. Similarly, the camera serving as a sensor can detect other variables and accordingly manipulate the actuator. In addition, a microphone serving as a sensor not affected by the actuator can detect the ambient volume and accordingly manipulate the actuator that outputs sound and other actuators in a manner different from the initial target setting. The artificial intelligence unit can decide all of this.

[0020] The motor vehicle according to the invention includes a controller in which an artificial intelligence unit is implemented, in particular by means of a neural network of the controller. The motor vehicle also includes an actuator. A set including a plurality of parameter values specifies a plurality of target settings for these pre-determined actuators, where each target setting is assigned to a target value of the pre-determined input variable, and where the artificial intelligence unit is designed to change at least one parameter value in the set when there is a deviation between the actual value and the target value of the pre-determined input variable, and where the controller is designed to manipulate the actuator according to the changed set of parameter values. The motor vehicle implements the method for manipulating at least two actuators as described above.

[0021] The controller according to the invention for a motor vehicle of the type just described includes means for providing an artificial intelligence unit, in particular also including a neural network, where a set including a plurality of parameter values is stored in the memory of the controller, and this set specifies a plurality of target settings for these pre-determined actuators, where for at least one actuator, and preferably each target setting is assigned to a target value of the pre-determined input variable, and where the means for providing the artificial intelligence unit of the controller is designed to change at least one parameter value in the set when there is a deviation between the actual value and the target value of the pre-determined input variable, and where the controller is designed to output a control signal to the actuator according to the changed set of parameters.

[0022] The method for operating a motor vehicle according to the invention is likewise implemented using an artificial intelligence unit, the aim of the method being in particular to provide an in-vehicle experience, wherein the method can be carried out in different motor vehicles, optionally with or without a predetermined actuator. For at least one predetermined actuator, it is determined whether the at least one predetermined actuator is present in the motor vehicle to be operated. A set of parameter values defines a plurality of target settings for the actuators including the predetermined actuator, and in the case where the predetermined actuator is not present in the motor vehicle, the artificial intelligence unit activates at least one additional actuator and / or changes the parameter values for the at least one additional actuator with respect to the target settings of the at least one additional actuator. The method corresponds to the method for controlling at least two actuators described above, wherein the target value of the predetermined input variable is specified in binary form: whether the corresponding actuator is present in the motor vehicle.

[0023] For application cases or use cases that can be obtained in the method and are not explicitly described herein, it may be provided that an error report is output according to the method and / or a requirement for inputting user feedback, and / or standard settings are adjusted and / or a predetermined initial state is adjusted.

[0024] The invention further includes a control device for a motor vehicle. The control device may have a data processing device or a processor device, which is arranged to execute an embodiment of the method according to the invention. For this purpose, the processor device may have at least one microprocessor and / or at least one microcontroller and / or at least one FPGA (Field Programmable Gate Array) and / or at least one DSP (Digital Signal Processor). In addition, the processor device may have a program code, which is arranged such that when executed by the processor device, it executes an embodiment of the method according to the invention. The program code may be stored in the data memory of the processor device. The processor circuit of the processor device may have, for example, at least one circuit board and / or at least one SoC (System on Chip).

[0025] The invention further includes an improvement of a motor vehicle according to the invention, which has the features as described in connection with the improvement of the method according to the invention. For this reason, the corresponding improvement of the motor vehicle according to the invention will not be described in detail herein.

[0026] Preferably, the motor vehicle according to the invention is designed as a motor car, in particular as a passenger car or a commercial vehicle, or as a bus or a motorcycle.

[0027] As another solution, the present invention also includes a machine-readable storage medium, which includes a command that, when executed by a computer or a computer group, causes the execution of an embodiment of the method according to the present invention. The storage medium can be at least partially designed as a non-volatile data memory (e.g., flash memory and / or SSD-solid state drive, solid state hard disk) and / or at least partially designed as a volatile data memory (e.g., RAM-random access memory, random access memory). However, the storage medium can also be run on the Internet, for example, as a so-called APP store server. A processor circuit with at least one microprocessor can be provided by a computer or a computer group. The command can be provided as a binary code or as an assembly code and / or as a source code of a programming language (e.g., C).

[0028] The invention also includes combinations of features of the described embodiments. Therefore, the invention also includes implementations which each have a combination of features of a plurality of the described embodiments, as long as these embodiments are not described as mutually exclusive. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The following describes an embodiment of the present invention.

[0030] Figure 1 A motor vehicle is shown in which the present invention may be implemented; and

[0031] Figure 2 The steps of one specific embodiment of the method according to the invention are shown. DETAILED DESCRIPTION

[0032] The embodiments described below are preferred embodiments of the present invention. In the embodiments, the described parts of the embodiments are the individual features of the present invention that can be regarded as independent of each other, and these features also improve the present invention independently of each other. Therefore, the present disclosure should also include feature combinations that are different from the illustrated embodiment feature combinations. In addition, the described embodiments can also be supplemented by other features in the already described features of the present invention.

[0033] In the figures, the same reference numerals respectively denote elements with the same function.

[0034] exist Figure 1 The motor vehicle shown as a whole in the figure and denoted here by reference numeral 1 is intended to provide an interior experience of the passenger compartment for an occupant 2. For this purpose, a controller 10 is provided, in which a device for providing an artificial intelligence unit is implemented by using a neural network. The controller controls actuators 12a, 12b, 12c, 12d and receives signals from sensors 14a, 14b, 14c.

[0035] That is, for example, the first actuator 12a can be a light-emitting diode or other strip-shaped light source in the vehicle ceiling. The actuator 12b adjusts the (multiple) seat positions of the vehicle occupant 2's seat. The display 12c displays images and other display content, and the speaker 12d is used to output sound. Other actuators can also be involved (for example, to provide heat, such as seat heating and hot air ventilation; humidification or dehumidification, and many other functions).

[0036] The first sensor 14a is designed as a camera facing the surrounding environment of the motor vehicle. In this example, for example, it detects the sky above the motor vehicle. The second sensor 14b can detect the seat position. The seat position can be the result of the controller 10 controlling the actuator 12b, and more precisely, it is also an indirect result of the vehicle occupant 2 operating on the input device 16 that generally exists here. Another sensor 14c can, for example, detect temperature and / or air humidity. Through the input device 16, the vehicle occupant 2 can indicate their user preferences. For example, the occupant can input the temperature that is preferred for the in-vehicle experience, whether the occupant likes to listen to music at a particularly low volume or prefers to listen to music at a medium volume, and many more.

[0037] The method according to the present invention includes storing, in the controller 10, a set having a plurality of parameter values, and this set should define the in-cabin interior experience. If necessary, this set can also be wirelessly received from an external unit ("backend") through the communication interface 18. However, the set of parameter values does not always perfectly give the in-cabin interior experience. It is possible that, for the actuator, the set target setting cannot be achieved at all, for example, because the vehicle occupant 2 has made a setting.

[0038] Accordingly, in step S12, the sensor device can detect the actual setting. In step S14, the target setting is compared with the actual setting. If there is a deviation between the actual setting and the target setting, then in step S16, at least one parameter value is changed. For example, it is possible that the vehicle occupant 2 confirms through the input device that the music should be played at a lower volume. Then, correspondingly, a weak blue light ("similar to the night sky") can be output through the actuator 12a instead of the set white light or red light. The artificial intelligence unit 10 ensures that - after autonomous learning if necessary, taking into account the active feedback of the vehicle occupant 2 or detecting the reaction of the vehicle occupant through the sensor device - the in-vehicle experience obtained by the vehicle occupant 2 basically conforms to the original setting, or only deviates to the extent caused by the operation of the vehicle occupant 2 (adjusting the seat or other actuators, making an input at the input device 16).

[0039] After step S16, usually (if the in-vehicle experience is not over), return to step S10, and optionally repeat step S12 in parallel.

[0040] Generally speaking, the examples show how an audio studio experience environment can be provided.

Claims

1. A method for controlling at least two actuators (12a, 12b, 12c, 12d) of a motor vehicle (1) in the case of using an artificial intelligence unit, the aim of the method being in particular to provide an in-vehicle experience, wherein, A target setting is specified for at least one predetermined actuator (12a, 12b, 12c, 12d), the target setting being assigned to a target value of a predetermined input variable, wherein when there is a deviation between the actual value of the predetermined input variable and the target value of the predetermined input variable, the artificial intelligence unit changes the target setting for at least one predetermined actuator (12a, 12b, 12c, 12d).

2. The method according to claim 1, characterized in that, Target settings are preset for at least two predetermined actuators (12a, 12b, 12c, 12d), wherein the target setting of one predetermined actuator defines the target value of the predetermined input variable, and wherein when there is a deviation between the actual setting of the one predetermined actuator and its target setting, the artificial intelligence unit changes the target setting for another predetermined actuator.

3. The method according to claim 2, characterized in that, The user can manipulate at least some of the predetermined actuators such that the at least some actuators deviate from their target settings, wherein the artificial intelligence unit changes the target settings for another part of the predetermined actuators that are not manipulated by the user.

4. The method according to any one of claims 1 to 3, characterized in that, The predetermined input variable is a variable reflecting the user's preference.

5. The method according to claim 4, characterized in that, The predetermined input variable is represented numerically.

6. The method according to any one of claims 1 to 5, characterized in that, The target setting can be changed by the user at least partially, preferably completely.

7. The method according to any one of claims 1 to 6, characterized in that, The predetermined input variable is a variable detected by at least one sensor (14a, 14b, 14c), wherein the sensor is not affected by the actuator.

8. A motor vehicle (1) having a controller (10) in which an artificial intelligence unit is implemented, in particular by means of a neural network, the motor vehicle having actuators (12a, 12b, 12c, 12d), wherein, At least one set comprising a plurality of parameter values specifies a plurality of target settings for a predetermined actuator (12a, 12b, 12c, 12d), wherein at least for some of the actuators, the target setting, preferably each target setting, is assigned to a target value of a predetermined input variable, and wherein the artificial intelligence unit is designed to change at least one parameter value in the set when there is a deviation between the actual value and the target value of the predetermined input variable, and wherein the controller (10) is designed to control the actuator (12a, 12b, 12c, 12d) according to the changed set of parameter values.

9. A controller for a motor vehicle (1) according to claim 8, the controller having means for providing an artificial intelligence unit - in particular a neural network - wherein, A set comprising a plurality of parameter values is stored in the memory of the controller (10), the set specifying a plurality of target settings for a predetermined actuator (12a, 12b, 12c, 12d), wherein at least for some of the actuators, the target setting, preferably each target setting, is assigned to a target value of a predetermined input variable, and wherein the means for providing the artificial intelligence unit is designed to change at least one parameter value in the set when there is a deviation between the actual value and the target value of the predetermined input variable, and wherein the controller is designed to output a control signal to the actuator (12a, 12b, 12c, 12d) according to the changed set of parameters.

10. A method for operating a motor vehicle (1) in the case of using an artificial intelligence unit, the aim of the method being in particular to provide an in-vehicle experience, wherein, The method can be executed selectively in different motor vehicles, with or without a predetermined actuator. For at least one predetermined actuator, it is determined whether the at least one predetermined actuator is present in the motor vehicle to be operated. A set of parameter values defines a plurality of target settings for the actuators including the predetermined actuator. In the case where the predetermined actuator is not present in the motor vehicle, the artificial intelligence unit activates at least one additional actuator and / or changes the parameter values for at least one additional actuator with respect to the target settings.

Images