DE102022122441B3 - Motor vehicle and method for providing a protective function for the motor vehicle - Google Patents

Abstract

The invention relates to a motor vehicle and a method for providing a protective function for the motor vehicle (10). The method comprises the steps of acquiring (S10) image data from at least one vehicle occupant (16) by an imaging recording device (12), wherein a position of the vehicle occupant (16) in the motor vehicle (10) is additionally determined; determining (S12) an age of the at least one vehicle occupant (16) from the image data by a trained AI algorithm; and if the determined age of the vehicle occupant (16) is below an age threshold and the position of this vehicle occupant (16) is determined to be in a driver position, activating (S14) the protective function of the motor vehicle (10) by a control device (14), whereby the Protective function prevents manual control of the motor vehicle (10).

Description

The invention relates to a method for providing a protective function, in particular immobilization protection, for a motor vehicle and a motor vehicle that is designed to carry out the method.

There may be a scenario where a child is playing in a motor vehicle without the parent's knowledge and may start it. This poses a danger to the child and other road users. Furthermore, autonomous vehicles enable driverless driving, which requires very little attention when operating the vehicle. In the future, it may be possible for a vehicle to drive to the destination independently by speaking or briefly entering the destination. Due to the low complexity of putting an autonomous vehicle into operation, the risk of minors or children accidentally or knowingly putting a vehicle into operation increases. This can also pose a danger to other road users, as a driver often has to intervene in unsafe situations. In addition, with many autonomous vehicle concepts it will be possible to switch to manual driving while driving autonomously, which could have serious consequences if the driver is a child.

From the DE 10 2021 126 878 A1 Systems and methods for parental protection of a vehicle against movement with child detection are disclosed. The method includes determining the presence of a known child in a vehicle, activating an immobilizer mode of the vehicle based on the presence of the known child to prevent driving of the vehicle, providing an authorization request to enable driving of the vehicle, and continuing or deactivating the Using the vehicle immobilizer mode based on the response to the authorization request.

From the DE 10 2017 203 738 A1 an assistance system for a means of transport with an operating mode for fully automated movement control is disclosed, wherein at least one piece of interior information about a means of transport occupant or about a transport object in the interior of the means of transport can be determined by means of a sensor connected to a safety control unit, and an operating element depending on the interior information and a Communication interface can be overridden by the safety control unit.

From the US 11 193 312 B1 A child lock is known, with an apparatus having a recording device and a processor. The recording device is configured to generate a plurality of video frames that correspond to an interior view of the vehicle. The processor is configured to perform operations on the video frames to detect objects in the video frames, determine an occupant of the vehicle and a seat of the vehicle based on the objects detected in the video frames, a status of the vehicle occupant based on characteristics of the vehicle occupant in the Determine video frames and determine a signal in response to a comparison of the vehicle occupant's status to a threshold value. The signal is configured to control a door lock.

From the WO 2017/040929 A1 a method and an apparatus for controlling use of an autonomous vehicle are known. The apparatus includes an interior occupant detection system for obtaining data from occupants through a video camera. An occupant recognition controller is configured to receive the video and recognize a number of faces of occupants located in the vehicle. Further, the occupant detection controller determines demographic information from the video data of each detected face, and then stores the vehicle position, the number of faces, and the demographic information of the occupants as data in the vehicle. The occupant detection controller determines an age of the occupants in the autonomous vehicle from the demographic information, and if the demographic information indicates that all occupants in the autonomous vehicle are under a certain age, travel to a destination or operation of the autonomous vehicle in response to that Age limited. Further, the occupant recognition controller may recognize a specific authorized individual in the vehicle and restrict use of the vehicle for the identified authorized individual.

The object of the invention is to increase safety for a motor vehicle.

This task is solved by the independent patent claims. Advantageous further developments are disclosed in the dependent patent claims, the following description and the figures.

The invention is based on the idea that age detection is carried out using imaging methods and a trained, intelligent algorithm. The algorithm is used with image data from people at different points in time fed with life. This means that a person A is photographed at different points in life and fed to the algorithm. The algorithm can now contextualize the visual signs of age with the actual age of other people, which works particularly well for young people. This means that a decision can be made automatically as to whether a vehicle occupant is authorized to drive the vehicle.

The invention relates to a method for providing a protective function for a motor vehicle, comprising the steps of acquiring image data from at least one vehicle occupant by an imaging recording device, wherein a position of the vehicle occupant in the motor vehicle is additionally determined, determining an age of the at least one vehicle occupant from the Image data by a trained Kl algorithm (artificial intelligence algorithm), and if the determined age of the vehicle occupant is below an age threshold and the position of this vehicle occupant is determined in a driver position, activating the protective function of the motor vehicle by a control device, wherein the protective function a manual control of the motor vehicle is prevented.

In other words, one or more vehicle occupants who are in the motor vehicle are first recorded by an imaging recording device. The imaging recording device can include, for example, one or more cameras, in particular video cameras and/or infrared cameras, for creating image data from each vehicle occupant. Furthermore, it is determined at which position in the motor vehicle the respective vehicle occupant is. For example, the imaging recording device or another device, in particular a seat occupancy sensor, can determine whether a person is in a driver position or a passenger position. The driver position means the position in the motor vehicle from which the motor vehicle can be controlled. An age determination can then be carried out using the recorded image data by using a trained artificial intelligence algorithm (AI algorithm) to analyze the image data. The AI algorithm can be trained with training image data, in particular with images of people whose age is known at the time of recording, in order to recognize age characteristics. These learned age characteristics can then be applied to the captured image data to estimate the age of the respective vehicle occupant.

The age determined in this way can be transferred to a control device, which can check as a condition whether the determined age of the respective vehicle occupant is below an age threshold or not. The age threshold can preferably be determined according to legal regulations, in particular whether driving a motor vehicle is permitted at that age or not. Furthermore, the control device can check whether the position of the vehicle occupant whose age is below the age threshold is in the driver's position of the motor vehicle. If it is determined that both the determined age of the vehicle occupant is below the age threshold and the position of this vehicle occupant is in the driver position, the control device can activate a protective function which prevents manual control of the motor vehicle. This means, for example, that an immobilizer can be activated automatically if the aforementioned conditions apply. If at least one of the aforementioned conditions does not apply, it can be provided that the motor vehicle can be started and controlled normally.

This method can preferably also be extended to other areas. For example, to other people under protection, such as people with dementia and/or people who are unable to drive, who are trying to drive the motor vehicle.

The invention has the advantage that minors who are not authorized to drive can no longer start and/or operate the motor vehicle. This can increase safety in road traffic.

Furthermore, it is provided according to the invention that after stopping and restarting a journey, a check process takes place by the AI algorithm as to whether vehicle occupants who were identified as being below the age threshold are in the motor vehicle, with the protective function being activated if the vehicle occupants are below the age threshold is not in the motor vehicle. This check can preferably take place if the vehicle occupant is below the age threshold when starting the journey and is in a passenger position and a stopping process, for example at a rest area, takes place during the journey. The control device can create an avatar for each vehicle occupant from the videos/images while driving and save it, for example, in a ring memory. As soon as the motor vehicle is stopped, which can be indicated, for example, by deactivating the engine and/or opening the doors, the control unit can check whether all previous occupants, in particular those below the age threshold, are still in the motor vehicle after the journey has started again. If not, the protective function and thus an immobilizer can be issued, preferably additionally with a warning, that a person is no longer in the vehicle. This warning can be issued, for example, via an image/video display. Particularly preferably, a driver or passenger can then confirm or deactivate this warning and the protective function if the intention was to let the person out at this point. If the absence of one or more vehicle occupants is confirmed, the control unit can delete the data on the created avatars, i.e. the ring buffer, which represents data protection compliance. Optionally, avatars can also be saved and given names so that inmates can be recognized more quickly in the future. This has the advantage that safety can be further increased since vehicle occupants, especially those below the age threshold, can no longer be accidentally forgotten after a stop.

The invention also includes embodiments that provide additional advantages.

One embodiment provides that the method is started when a starting process of the motor vehicle is detected by the control device and/or a manual control is requested in an autonomous motor vehicle. In other words, the protective function can include an immobilizer and/or a prevention of taking over manual control in an autonomously driving motor vehicle. A starting process can, for example, be starting the motor vehicle with a key, in which case the method and the age determination can then be started. Alternatively or additionally, the motor vehicle can be an autonomously driving motor vehicle, whereby in the case of an autonomously driving motor vehicle, manual control or control can be requested while driving. To ensure that this is not handed over to an underage driver without a driving license, the procedure can check whether the current driver is authorized to take over manual control. This embodiment has the advantage that security can be further increased.

It is preferably provided that the imaging recording device has at least one camera and/or an infrared camera and/or an ultrasonic sensor. The camera can preferably record moving images in a visible spectral range, the infrared camera can record images in a thermal imaging range and the ultrasonic sensor can preferably capture contours of a face via ultrasound detection. Furthermore, for example, a laser scanner, in particular a lidar, can also be provided for recording image data. This results in preferred embodiments for the imaging recording device.

A further embodiment provides that a voice recording is additionally recorded by an acoustic recording device, with the trained AI algorithm or another trained AI algorithm also carrying out an age determination using the voice recording. For example, in vehicles, in particular autonomous vehicles, control or destination entry to a destination can take place via a voice command. The voice recording for this voice command can also be evaluated by an AI algorithm that was trained using voice recordings from different age groups. The AI algorithm can preferably compare a voice pitch, syntax and/or sentence structure with trained voice recordings of the respective age group and thus also decide what age a vehicle occupant is. The acoustic recording device can, for example, be an interior microphone in the vehicle, by means of which voice control and/or a telephony function is possible. This embodiment has the advantage that age determination can be improved.

A further embodiment provides that the position of the at least one vehicle occupant is determined by a seat occupancy sensor, with the seat occupancy sensor additionally determining a weight of the vehicle occupant, with the trained AI algorithm or a further trained AI algorithm also determining age by means of the determined weight is carried out. The determination of the position of the vehicle occupant in the motor vehicle can be carried out either by the imaging recording device and/or by means of a seat occupancy sensor, which can determine the occupancy of a seat or a position in the motor vehicle via pressure sensors. The seat occupancy sensor can preferably also be designed to determine the weight of the vehicle occupant in this position, whereby the weight can be evaluated together with the image data in order to determine an age. For example, a gender and/or height of the vehicle occupant can be determined from the image data, and this data can then be related to a weight of people of different age groups, which was measured with the seat occupancy sensor. This means that it can preferably be further checked for plausibility as to whether the age estimated by the AI algorithm is correct. which can improve age determination.

A further embodiment provides that if the determined age of the vehicle occupant is below the age threshold, a youth protection function is activated for an infotainment offer. Regardless of the position in the motor vehicle, if the age is below the age threshold, provision can be made for the youth protection function to be activated. For example, as an infotainment offering, music, films, websites and/or a telephony function can be restricted by the child protection function, preferably depending on the determined age. This means that, for example, only infotainment offers are made available that have a child protection rating below the established age. This embodiment has the advantage that protection for minors can be further increased.

A further embodiment provides that the activated protective function is deactivated by the AI algorithm by comparing the vehicle occupant's face with the vehicle occupant's driver's license. In other words, in order to deactivate the protective function and thus enable manual control, it can be provided that a vehicle occupant for whom an age below the age threshold has been recognized can hold his driver's license in the imaging recording device, whereby the AI algorithm does this Compares the image of the driver's license with that of the vehicle occupant and, if there is a match, causes the protective function to be deactivated. It can be difficult to distinguish between ages, particularly in the transition to adulthood or driving license age. In order to still be able to control the motor vehicle in this case or if the age is incorrectly determined, the protective function can preferably be bridged by using an identification process. This embodiment has the advantage that it can be ensured that the vehicle occupant is authorized to drive.

A further embodiment provides that the AI algorithm is trained using training image data from people who were taken at different ages. This means that several people, for whom image data was recorded at different times, serve as training image data for the algorithm. For example, training image data may be available from a person aged 5 years, 12 years and 17 years, which can be used to teach age characteristics. Particularly preferably, real images of the vehicle occupants, for example a family of the vehicle owner, can also serve as training data for the algorithm, whereby the age determination can be further improved.

Another aspect of the invention relates to a motor vehicle that is designed to carry out a method according to one of the preceding embodiments. For this purpose, the motor vehicle can include an imaging recording device and a control device on which a trained AI algorithm is operated. The imaging recording device can be designed to capture image data from at least one vehicle occupant, with a position of the vehicle occupant in the motor vehicle also being able to be determined. The AI algorithm can be designed to determine an age of the at least one vehicle occupant from the image data, the control device being designed to activate a protective function of the motor vehicle if the determined age of the vehicle occupant is below an age threshold and the position of this vehicle occupant is on a Driver's position is, manual control of the motor vehicle being blocked by the protective function. This results in the same advantages and possible variations as with the process.

For use cases or application situations that may arise with the method and that are not explicitly described here, it can be provided that an error message and/or a request to enter user feedback and/or a standard setting and/or a predetermined one can be issued according to the method Initial state is set.

The invention also includes the control device for the motor vehicle. The control device can have a data processing device or a processor device that is set up to carry out an embodiment of the method according to the invention. For this purpose, the processor device can 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). Furthermore, the processor device can have program code that is designed to carry out the embodiment of the method according to the invention when executed by the processor device. The program code can be stored in a data memory of the processor device. A processor circuit of the processor device can, for example, have at least one circuit board and/or at least one SoC (System on Chip).

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

The motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a passenger car or truck, or as a passenger bus or motorcycle.

As a further solution, the invention also includes a computer-readable storage medium comprising instructions which, when executed by a computer or a computer network, cause it to carry out an embodiment of the method according to the invention. The storage medium can, for example, be designed at least partially as a non-volatile data storage (e.g. as a flash memory and/or as an SSD - solid state drive) and/or at least partially as a volatile data storage (e.g. as a RAM - random access memory). . The storage medium can also be operated on the Internet as a so-called app store server, for example. The computer or computer network can provide a processor circuit with at least one microprocessor. The instructions may be provided as binary code or assembler and/or as source code of a programming language (e.g. C).

The invention also includes the combinations of the features of the described embodiments. The invention therefore also includes implementations that each have a combination of the features of several of the described embodiments, provided that the embodiments have not been described as mutually exclusive.

• 1 ein Kraftfahrzeug gemäß einer beispielhaften Ausführungsform;
• 2 ein schematisches Verfahrensdiagramm gemäß einer beispielhaften Ausführungsform.

Examples of embodiments of the invention are described below. This shows:

• 1 a motor vehicle according to an exemplary embodiment;
• 2 a schematic process diagram according to an exemplary embodiment.

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 that can be viewed independently of one another and which also further develop the invention independently of one another. Therefore, the disclosure is intended to include combinations of the features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by further features of the invention that have already been described.

In the figures, the same reference numerals designate functionally identical elements.

In 1 a motor vehicle 10 is shown according to an exemplary embodiment. The motor vehicle 10 can be a passenger car, wherein the motor vehicle 10 can be operated manually and/or autonomously. In order to be able to provide a protective function against unauthorized starting of the motor vehicle 10 by minors, the motor vehicle 10 has at least one imaging recording device 12 and a control device 14. The imaging recording device 12 can preferably have at least one camera and/or infrared camera and/or an ultrasonic sensor, which are designed to record image data of a person, in particular of a person's face.

The control device 14 can be a control device of the motor vehicle 10, wherein the control device 14 can have at least one processor and a memory through which an algorithm for artificial intelligence (AI algorithm) can be operated on the control device 14. The AI algorithm is preferably trained with image data from people at different ages in order to recognize age characteristics. The AI algorithm can be trained with training image data from people at different ages, which means that, for example, a person A is trained with a plurality of image data at different ages, for example between 5 years and 21 years. The AI algorithm can learn age characteristics for a given age in order to determine age using the image data provided.

In an exemplary situation, it can be provided that a vehicle occupant 16 is a child who is not authorized to drive the motor vehicle 10. When the motor vehicle is started by the child 16 and/or during an autonomous journey with the motor vehicle 10, during which manual control is requested, the control device 14 can control the imaging recording device 12 in order to record image data of the vehicle occupant 16. In addition, a position of the vehicle occupant 16 in the motor vehicle 10 can be determined by the imaging recording device 12 and/or a seat occupancy sensor 18. In this case, it can be determined, for example, that the vehicle occupant 16 is in a driving position.

The image data captured in this way can then be analyzed by the control device 14 in that the trained AI algorithm determines signs of age characteristics from the image data and can thus estimate the age of the vehicle occupant 16. The control device 14 can then check whether the determined age is below or above an age threshold. The age threshold can be specified, for example from legal requirements for driving a motor vehicle.

If the determined age is below the age threshold and at the same time the position of the vehicle occupant 16 is in the driver's position, the control device 14 can activate a protective function that prevents manual control of the motor vehicle 10. This means that either an immobilizer can be activated and/or taking over manual control during autonomous driving can be prevented. Thus, the child 16 cannot start or drive the motor vehicle 10, which increases safety for the child 16 and other road users.

In order to further improve the age determination, it can also be checked whether a weight of the vehicle occupant 16 matches a weight of a predetermined age group. For this purpose, the seat occupancy sensor 18 can additionally determine a weight of the vehicle occupant 16, whereby the weight data can be made available to the control device 14. A gender, a height and an estimated age can be determined from the recorded image data, so that a weight range of an age group and a gender can be selected with which the determined weight of the seat occupancy sensor 18 is compared. If this weight is within the weight range, it can be assumed that the age determination by the AI algorithm is correct.

Alternatively or additionally, a voice recording of the vehicle occupant 16 can be analyzed to further improve the age determination. For this purpose, an acoustic recording device 20 can be provided in the motor vehicle 10, wherein the acoustic recording device 20 can include one or more microphones. For example, voice commands for controlling the motor vehicle, in particular for entering a destination, can be provided, with the acoustic recording device 20 recording a voice recording of this voice command and making it available to the control device 14. The trained AI algorithm or another trained AI algorithm, which can preferably be trained with voice data, can then check the voice recording for age characteristics. In this way, a pitch, sentence structure and/or syntax that are characteristic of different age groups can be analyzed. If the age determined from the voice recording matches the age from the image data analysis, the age determination can be verified. If these do not match, there may be an uncertainty factor in the age determination, in which case the younger estimated age can preferably be assumed.

In addition to the protective function, that is to say the immobilizer and/or taking over manual control, a youth protection function for an infotainment offer can be activated by the control device 14 when the age of the vehicle occupant 16 is detected below the age threshold. This can be activated regardless of a position of the vehicle occupant 16 in the motor vehicle. The youth protection function can be carried out depending on the determined age, so that only infotainment offers that correspond to the determined age are provided. An infotainment offer can be a restriction of a music offer, a film offer and websites that can be accessed using an infotainment system (not shown). Furthermore, depending on age, a telephony function can be restricted so that, for example, only specified telephone numbers can be called.

An age comparison can be provided so that the protective function and/or the youth protection function is deactivated if, for example, an age has been incorrectly recognized, which can happen in particular in a transition area to adulthood. For this purpose, for example, an identification document, in particular a driver's license, can be held for recording in the imaging recording device 12, whereby this data can then be transmitted to the control device 14 together with the recorded image data of the vehicle occupant 16. The AI algorithm can then carry out a facial comparison between the identification document and the recorded image of the vehicle occupant 16 and preferably automatically verify the identification document. Particularly preferably, the AI algorithm can recognize a driver's license and compare whether the image of the driver's license matches the vehicle occupant 16. If this is the case, the control device 14 can deactivate the security function and/or the child protection function.

In another exemplary situation, an authorized driver may be driving the motor vehicle 10 and the child is seated in a passenger position. The AI algorithm can determine the respective age and, for example, automatically create avatars for each vehicle occupant in a ring buffer save. If the motor vehicle 10 stops while driving, which can be determined, for example, by deactivating the engine and / or opening the vehicle doors, after the journey starts again, a check process can take place by the AI algorithm as to whether all vehicle occupants are in the motor vehicle 10 again, in particular by comparing the avatars stored in the ring buffer. Here, special attention can preferably be paid to whether the child is in the motor vehicle 10 again. If this is not the case, the control device 14 can activate the protective function together with a warning message that, for example, displays an image of the avatar that is missing.

This means that preferably no child can be accidentally forgotten after a stop. If it is planned to intentionally let the child out at the holding position, for example to take him to school or kindergarten, the protective function can be deactivated by confirming the warning, preferably by entering a password. The ring buffer can then be deleted or the avatars can optionally be saved in order to recognize the occupants more quickly in the future.

In 2 a schematic process diagram for providing a protective function for a motor vehicle 10 is shown. In a step S10, image data of at least one vehicle occupant 16 can be recorded by an imaging recording device 12, wherein a position of the vehicle occupants 16 in the motor vehicle 10 can additionally be determined, for example by a seat occupancy sensor 18 of the motor vehicle 10. Alternatively, the imaging recording device 12 can also Determine the position of the vehicle occupants 16 in the motor vehicle 10.

In a step S12, the age of the respective vehicle occupants can be determined from the image data by a trained AI algorithm. The AI algorithm can be trained using training image data from people whose age is known. Thus, images of the faces and/or the body structure of the vehicle occupants 16 can preferably be compared with the training image data in order to determine similarities with a specific age group in order to determine the age from this. In addition to the age determination from the image data, an age determination can also be carried out from a voice recording, which is recorded using an acoustic recording device 20. A weight comparison based on a weight that is determined by the seat occupancy sensor 18 can also be included in the age determination.

After the age has been determined, a control device 14 can check in a step S14 whether the determined age of one of the vehicle occupants 16 is below an age threshold, the age threshold representing authorization to drive the motor vehicle 10. If a vehicle occupant 16 has been identified whose age is below the age threshold, it can also be determined whether the position of this vehicle occupant 16 in the motor vehicle 10 is in the driver position, with a protective function being activated only if the two aforementioned conditions apply manual control of the motor vehicle and/or a start of the motor vehicle 10 is prevented.

Overall, the examples show how the invention can provide AI immobilization protection for minors and those under protection.

Claims (9)

Method for providing a protective function for a motor vehicle (10), comprising the steps: - Acquiring (S10) image data of at least one vehicle occupant (16) by an imaging recording device (12), wherein a position of the vehicle occupant (16) in the motor vehicle (10) is additionally determined; - Determining (S12) an age of the at least one vehicle occupant (16) from the image data by a trained AI algorithm; - If the determined age of the vehicle occupant (16) is below an age threshold and the position of this vehicle occupant (16) is determined in a driver position, activating (S14) the protective function of the motor vehicle (10) by a control device (14), wherein by the protective function manual control of the motor vehicle (10) is prevented; - whereby after a stop and restart of a journey, a check process takes place by the AI algorithm as to whether vehicle occupants (16) who were identified as being below the age threshold are in the motor vehicle (10), the protective function being activated if the vehicle occupants are (16) under the age threshold are not in the motor vehicle (10). Procedure according to Claim 1 , wherein the method is started when a starting process of the motor vehicle (10) is detected by the control device (14) and/or a manual control is requested in an autonomous motor vehicle (10). Method according to one of the preceding claims, wherein the imaging recording Direction (12) has at least one camera and / or infrared camera and / or an ultrasonic sensor. Method according to one of the preceding claims, wherein an acoustic recording device (20) additionally records a voice recording, wherein an age determination is additionally carried out by means of the voice recording by the trained AI algorithm or a further trained AI algorithm. Method according to one of the preceding claims, wherein the position of the at least one vehicle occupant (16) is determined by a seat occupancy sensor (18), wherein a weight of the vehicle occupant (16) is additionally determined by the seat occupancy sensor (18), with the trained AI Algorithm or another trained AI algorithm an age determination is also carried out using the determined weight. Method according to one of the preceding claims, wherein if the determined age of the vehicle occupant (16) is below the age threshold, a child protection function is activated for an infotainment offer. Method according to one of the preceding claims, wherein the activated protective function is deactivated by the AI algorithm by means of a facial comparison of the vehicle occupant (16) with a driver's license of the vehicle occupant (16). Method according to one of the preceding claims, wherein the AI algorithm is trained using training image data from people who were taken at different ages. Motor vehicle (10) which is designed to carry out a method according to one of the preceding claims.

Images