SYSTEM AND METHOD FOR CONTROLLING THE MOVEMENT OF A CHILD SEAT IN A VEHICLE BY GESTURES

Abstract

The present disclosure relates to a system (114) and a method (300) for controlling a child seat in a vehicle (102) using gestures. The system (114) receives audio and video data from an occupant. The system (114) extracts audio features from the audio data and video features from the video data that indicate gesture inputs from an occupant. The system (114) determines one or more rocking parameters for a child seat (106-2) based on the extracted audio and video features using a fuzzy inference machine, wherein the rocking parameters include frequency, amplitude, and direction. The system (114) controls a rocking mechanism of the child seat (106-2) based on the rocking parameters.

Description

TECHNICAL AREA

[0001] The present disclosure relates to devices / equipment for interacting with children in vehicles and in particular to a system and method for controlling the movement of a child seat (e.g. controlled rocking) in a vehicle based on user inputs / gestures. BACKGROUND

[0002] The safety of children in vehicles has been a primary concern for parents and caregivers for decades. Despite advances in vehicle technology, keeping young children calm and content during car journeys remains a significant challenge for many parents. Long car trips can be stressful for infants and toddlers, causing them to become restless, uncomfortable, or agitated. This not only affects the child's well-being but can also seriously distract the driver and compromise the safety of everyone in the vehicle.

[0003] One of the most effective methods to calm and comfort a child, especially infants and toddlers, is the use of lullabies and gentle rocking motions. Traditionally, parents have sung lullabies while rocking or cradling their children to create a soothing and nurturing environment.

[0004] Ensuring a child's comfort during car travel is becoming increasingly difficult. While current child car seats are designed to secure children during the journey, they don't offer the soothing movements or comfort that many children need. These seats prioritize safety above all else and lack features that address children's emotional and comfort needs during the trip. As a result, parents often find themselves in situations where their child becomes restless or agitated during the journey and requires comfort and attention that the seat itself cannot provide.

[0005] Singing lullabies and using soothing gestures like head bobbing are common techniques parents use to calm their children. However, these activities pose significant safety risks while driving. Taking your attention away from the road to interact with a child in the back seat can lead to dangerous situations and potential accidents.

[0006] Patent document JP2019034659A describes a vehicle system comprising a first detection system for detecting a predetermined action performed by a vehicle driver, a second detection system for detecting a movement of the driver that differs from the predetermined action, a determining means for determining whether the driver wishes to communicate with an occupant in a child seat based on the movement of the driver detected by the second detection system; and a control device for controlling the movement of a moving part to perform a movement corresponding to the predetermined action detected by the first detection system when it is determined that the driver wishes to communicate with the occupant in the child seat.

[0007] However, these documents do not take into account the important role of parental singing and lullabies in calming a child. They often offer a general rocking motion, and such solutions do not provide rocking combined with soothing air blown over the child. Furthermore, such solutions are unable to accurately recognize gestures, distinguish between gestures and normal head movements during the ride, and appropriately translate them into a suitable rocking routine.

[0008] Therefore, there is a need for improved systems and procedures for the personalized rocking of child car seats. SUBJECT OF THE PRESENT DISCLOSURE

[0009] One objective of the present disclosure is to provide a system and a method for controlling the rocking of child seats in a vehicle, which increases both the comfort of the children and the driving safety.

[0010] Another objective of this disclosure is to provide a system that translates the driver's / owner's natural actions, such as voice input (e.g., singing, humming, or speaking) and subtle physical gestures (e.g., head nodding or hand movements), into personalized rocking movements of the child seat.

[0011] Another purpose of the present disclosure is to provide a hands-free solution for calming a child in real time without distracting the driver.

[0012] Another function of the present revelation is to provide the child with calming air based on the gestures.

[0013] Another objective of this disclosure is to create a system that adapts over time to the preferences of both the driver and the child by using learning algorithms to personalize the experience and ensure effective, responsive calming actions. SUMMARY

[0014] Aspects of the present disclosure relate to devices / equipment for interacting with children in vehicles and in particular to a system and a method for controlling the movement of a child seat (e.g. controlled rocking) in a vehicle based on user inputs / gestures.

[0015] One aspect of the present disclosure relates to a system for providing a personalized child car seat in a vehicle, comprising a processor and memory operationally coupled to the processor. The memory contains one or more instructions executable by the processor which, when executed, cause the processor to receive audio and video data from a vehicle occupant. The processor is configured to extract audio features from the audio data and video features from the video data, which display gestures. The processor is further configured to determine one or more rocking parameters for a child car seat based on the audio and video features using a fuzzy inference engine. The one or more rocking parameters include frequency, amplitude, and direction.The processor is also configured to control a rocking mechanism of the child seat based on one or more rocking parameters.

[0016] In some embodiments, the fuzzy inference machine can be a Sugeno-type or Mamdani-type inference machine.

[0017] In some embodiments, the processor can further be configured to synchronize and combine the audio and video features to generate combined features. The processor can also be configured to determine one or more vibration parameters using the combined features.

[0018] In some embodiments, the processor for determining one or more vibration parameters can be configured to determine one or more corresponding scaling factors for that one or more vibration parameters. The processor can be configured to determine one or more scaling factors for the amplitude based on the audio intensity from the audio features and the size of the head nod from the video features. The processor can also be configured to determine one or more scaling factors for the frequency based on the rhythm and pitch from the audio features. Furthermore, the processor can be configured to determine one or more scaling factors for the direction based on the detected head direction from the video features.

[0019] In some embodiments, one or more scaling factors for one or more vibration parameters can be determined based on a predefined association function. This function assigns a value for one or more scaling factors to any one or a combination of the audio and video characteristics.

[0020] In some embodiments, a method for controlling a child seat in a vehicle using gestures comprises the reception of audio and video data from a vehicle occupant by a processor. The method also comprises the extraction by the processor of audio features from the audio data and video features from the video data displaying gestures. The method further comprises the determination by the processor of one or more rocking parameters for a child seat based on the audio and video features using a fuzzy inference engine. The one or more rocking parameters include frequency, amplitude, and direction. The method also comprises the control unit controlling a rocking mechanism of the child seat based on the rocking parameters.

[0021] In some embodiments, the fuzzy inference machine can be a Sugeno-type or Mamdani-type inference machine.

[0022] In some embodiments, the method further comprises the processor synchronizing and combining the audio and video features to generate combined features. The method also includes the processor determining one or more vibration parameters using the combined features.

[0023] In some embodiments, the method for determining one or more vibration parameters includes the processor determining one or more corresponding scaling factors for the one or more vibration parameters. The method also includes the processor determining one or more scaling factors for the amplitude, based on the audio intensity from the audio features and the head nod magnitude from the video features. The method further includes the processor determining one or more scaling factors for the frequency, based on the rhythm and pitch from the audio features. The method also includes the processor determining one or more scaling factors for the direction, based on the detected head direction from the video features.

[0024] In some embodiments, one or more scaling factors for one or more vibration parameters can be determined based on a predefined association function. This function assigns a value for one or more scaling factors to any one or a combination of the audio and video characteristics.

[0025] Various objects, features, aspects and advantages of the subject matter according to the invention will become clearer from the following detailed description of preferred embodiments together with the accompanying drawing figures, in which the same numbers represent the same components. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings serve to further understand the present disclosure and are an integral part of this description. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure. Fig. Figure 1 shows an exemplary architectural representation of a system for providing a personalized child seat in a vehicle according to the embodiments of the present disclosure. Fig. Figure 2 shows an exemplary block diagram of the system according to the embodiments of the present disclosure. Fig. Figure 3 shows an exemplary flowchart for a method for providing a personalized child seat in a vehicle according to the embodiments of the present disclosure. Fig. Figure 4 shows an exemplary computer system in which or with which embodiments of the system according to the embodiments of the present disclosure can be implemented. DETAILED DESCRIPTION

[0027] A detailed description of the embodiments of the disclosure illustrated in the accompanying drawings follows. The embodiments are described in sufficient detail to clearly convey the disclosure. However, the necessary level of detail is not intended to limit foreseeable variations of embodiments; on the contrary, it is intended to cover all modifications, equivalents, and alternatives that fall within the scope of this disclosure as defined by the accompanying claims.

[0028] The embodiments described herein relate to the field of interaction / intervention devices for children in vehicles and in particular to a system and a method for controlling the movement of a child seat (e.g. controlled rocking) in a vehicle based on user inputs / gestures.

[0029] One aspect of the present disclosure relates to a system and a method for controlling a child car seat in a vehicle using gestures. The system receives audio and video data from an occupant. The system extracts audio features from the audio data and video features from the video data that indicate gesture inputs from an occupant. Based on the extracted audio and video features, the system determines one or more rocking parameters for a child car seat using a fuzzy inference machine, wherein the rocking parameters include frequency, amplitude, and direction. The system controls a rocking mechanism of the child car seat based on the rocking parameters.

[0030] Various embodiments of the present disclosure are described with reference to Fig. 1-4 explained in more detail. 1-4.

[0031] Fig. Figure 1 shows an exemplary representation 100 of a vehicle 102. In some embodiments, the vehicle 102 may include a seat for a driver / user / occupant 104 of the vehicle 102, for example, a driver / user / occupant seat 106-1. In one example, the driver's seat 106-1 may be located in front of a steering wheel of the vehicle 102, normally on the left side in countries with right-hand traffic or on the right side in countries with left-hand traffic. In some embodiments, the vehicle 102 may also include a seat for an infant / child / baby / toddler 108, such as a child seat 104-2. The child seat 104-2 may be installed in various locations within the vehicle 102. For example, the child seat 104-2 may be installed in the rear of the vehicle 102 behind the driver's seat 106-1 or a front passenger seat.Alternatively, the child seat 104-2 can also be a separate seat that is not integrated into the original seating of the vehicle 102 and can be securely attached to one of the existing seats of the vehicle 102. In some embodiments, the child seat 104-2 can also be positioned in the front part of the vehicle 102 next to the driver's seat 106-1, e.g., in vehicles with deactivatable front passenger seats or in situations where rear seats are not available or practical.

[0032] In some embodiments, a video sensor 110 can be positioned in front of the driver 104 to capture the driver's gestures 104 as video data. In one embodiment, the video sensor 110 can be a camera integrated into the dashboard, instrument cluster, or infotainment system of the vehicle 102. In alternative embodiments, the video sensor 110 can be a separate camera attached to a windshield, rearview mirror, or wall of the vehicle 102. In some embodiments, the video sensor 110 can be a depth-sensing camera or a stereo camera to better capture three-dimensional movements. The video sensor 110 can also be part of a driver monitoring system that serves both for gesture recognition for controlling the child seat 106-2 and for monitoring the driver's attention. In other embodiments, the video sensor 110 can be a portable device, such as a smartphone.a smartphone or tablet that is temporarily mounted in the vehicle 102. In some embodiments, several video sensors 110 can be used, positioned at different angles to obtain a more comprehensive view of the driver's gestures 104. In some embodiments, the video sensor 110 can be equipped with infrared capabilities to ensure accurate gesture detection in low-light conditions or at night.

[0033] In some embodiments, the vehicle 102 may include an audio sensor 112 positioned near the driver's seat 106-1 to capture audio data from the driver 104. In one embodiment, the audio sensor 112 may be a microphone integrated into the interior of the vehicle 102, for example, in the steering wheel, dashboard, or overhead console, but not exclusively. In an alternative embodiment, the audio sensor 112 may be part of the vehicle 102's existing infotainment or hands-free system. In some embodiments, the audio sensor 112 may be a directional microphone specifically aimed at a position of the driver 104 to minimize ambient noise. In other embodiments, the audio sensor 112 may be an array of microphones distributed throughout the interior of the vehicle 102 to capture audio data from multiple angles, enabling better noise suppression and more accurate speech recognition.The audio sensor 112 can also be equipped with advanced digital signal processing functions to filter out road noise and other background noise. In some embodiments, a combination of near-field and far-field microphones can be used to capture both direct speech and ambient sounds that may be relevant to the comfort of the infant 108, such as music or a soft hum. In some embodiments, the audio sensor 112 can be a wearable device, such as a Bluetooth headset or smartwatch, worn by the driver 104 to enable more precise audio data capture. In some embodiments, the audio sensor 112 can also be designed to work in conjunction with the vehicle's active noise control 102, if present, to provide a clearer audio signal for processing.

[0034] In some embodiments, a system 114 (which may be part of an electronic control unit of the vehicle or a control unit within the vehicle 102) can be configured to acquire the video data acquired by the video sensor 110 and the audio data acquired by the audio sensor 112. The system 114 can be configured to extract audio features from the audio data and video features from the video data. The system 114 can be configured to combine the audio and video features to generate combined features. In one example, the combined features may include a set of data points that integrate information from both the audio and video features. The system 114 can be configured to determine one or more rocking parameters for the child seat 106-2 based on the extracted / combined features using a fuzzy inference engine (e.g., a 106-2).determined by a Sugeno-type or Mamdani-type inference machine. In one example, the swing parameters can include, but are not limited to, frequency, amplitude, and direction.

[0035] In some embodiments, the system 114 can be functionally coupled to a set of actuators 116. These actuators 116 can be electric motors, hydraulic systems, or a combination of both, coupled to the child seat 106-2 to enable the child seat 106-2 to move in multiple directions. The actuators 116 can be designed for precise control and smooth operation to ensure the comfort and safety of the infant 108. In one example, the system 114 can control the set of actuators 116 to control a rocking mechanism of the child seat 106-2 based on the rocking parameters.

[0036] While embodiments of the present disclosure are described in connection with the system 114, which is configured to detect gestures of the driver 104, the person skilled in the art can recognize that the system 114 can be suitably adapted to control the child seat 106-2 by detecting gestures of any user, occupant, or passenger in the vehicle 102. Furthermore, references to "infants 108" throughout the description may also include babies, infants, children, and the like.

[0037] Referring to block diagram 200 in Fig. 2. System 114 can contain one or more processors 202. The one or more processor(s) 202 can be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and / or any devices that process data based on operating instructions. Among other capabilities, the one or more processor(s) 202 can be configured to retrieve and execute computer-readable instructions stored in a memory 204. The memory 204 can store one or more computer-readable instructions or routines that can be retrieved and executed to create or share data units via a network service. The memory 204 can comprise any non-volatile device, such as...volatile memory such as Random Access Memory (RAM) or non-volatile memory such as Erasable Programmable Read-Only Memory (EPROM), Flash memory, and the like.

[0038] In one embodiment, the system 114 may also include one or more interfaces 206. The interface(s) 206 may include a variety of interfaces, such as interfaces for data input and output devices, referred to as I / O devices, storage devices, and the like. The interface(s) 206 may also provide a communication path for one or more components of the system 114. Examples of such components include the processing machine(s) 208 and the database 222. In some embodiments, the database 222 may store data generated or received by the system 114. For example, the database 222 may be configured to store the video data acquired by the video sensor 110, the audio data acquired by the audio sensor 112, and similar data.

[0039] In one embodiment, the processing machine(s) 208 can be implemented as a combination of hardware and programming (e.g., programmable instructions) to implement one or more functions of the processing machine(s) 208. In the examples described here, such combinations of hardware and programming can be implemented in various ways. For example, the programming for the processing machine(s) 208 can consist of processor-executable instructions stored on a non-volatile, machine-readable storage medium, and the hardware for the processing machine(s) 208 can include a processing resource (e.g., one or more processors) to execute such instructions. In other embodiments, the processing machine(s) 208 can be implemented by electronic circuits.Database 222 can contain data that is either stored or generated as a result of functionalities implemented by one of the components of processing machine(s) 208.

[0040] In some embodiments, the processing machine(s) 208 may comprise a communication machine 210, a feature extraction machine 212, a combined feature generation machine 214, an assignment machine 216, a control unit 218, and other machine(s) 220. The other machine(s) 220 may implement functionalities that complement the applications / functions performed by the system 114. In some embodiments, the other machines 220 may also include the fuzzy inference machine.

[0041] In some embodiments, the communication machine 210 can be configured to collect the video data captured by the video sensor 110 or the audio data captured by the audio sensor 112. In such embodiments, the communication machine 210 can communicate with the video sensor 110 each time the system 114 is activated by the driver 104, for example via a user interface of the vehicle's infotainment system 102, in order to obtain the video data corresponding to the gestures and body movements of the driver 104.In one example, the gestures and body movements performed by the driver 104 and detected by the video sensor 110 may include, but are not limited to, head nodding, head shaking, eyebrow raising, eye blinking, smiling, frowning, lip movements, hand gestures, shoulder shrugging, leaning forward or backward, tilting the head, winking, blinking, widening the eyes, pursing the lips, clenching the jaw, frowning, changes in posture, and exhaling. In one example, the driver 104 may perform the gesture of exhaling air through different mouth shapes, such as puffed-out cheeks with pursed lips or a more open mouth shape. The video sensor 110 can also detect more subtle movements such as changes in head orientation, microexpressions, and variations in blinking patterns. These gestures and body movements of the driver 104 may correspond to actions that parents commonly perform to monitor a child, for example.To soothe a small child 108, for example by singing lullabies. At the same time, the communication machine 210 can establish a connection with the audio sensor 112 to receive the audio data, which may include spoken words, humming, singing and / or other vocalizations by the driver 104.

[0042] In some embodiments, the feature extraction machine 212 can extract audio features from the audio data and video features from the video data. In one example, the audio features can include at least one of the pitch, rhythm, and intensity of the audio data. In another example, the video features include the detection of head nods and the detection of head direction from the video data. To extract the video features, the feature extraction machine 212 can employ a multi-stage process. In this process, the feature extraction machine 212 can use a pre-trained convolutional neural network (CNN) to, for example, detect and locate the face of driver 104 in each frame of the video stream of the video data. Once the face is detected, facial feature recognition algorithms, such as…The feature extraction machine 212 can apply an Active Shape Model (ASM), Active Appearance Model (AAM), or Constrained Local Model (CLM) to identify key points on the face, including the tip of the nose, the corners of the eyes, and the corners of the mouth of the driver 104. For example, using the detected facial features, the feature extraction machine 212 can estimate the orientation / coordinates of the driver 104's head in three-dimensional space. The feature extraction machine 212 can calculate the rotation angles (pitch, yaw, roll) of the head to determine the position and movement of the driver 104's head relative to the video sensor 110. The feature extraction machine 212 can focus on the vertical component of head movement to detect head nodding. The feature extraction machine 212 can establish thresholds for the vertical displacement of certain facial features (e.g.,The feature extraction machine 212 defines features (such as the tip of the nose for yaw detection, ears for tilt detection, etc.) over time to detect head nodding. A smoothing filter, such as a moving average or a Kalman filter, can be applied to the displacement signal by the feature extraction machine 212 to reduce noise and improve detection accuracy. The feature extraction machine 212 can then analyze the temporal patterns of the vertical displacement signal to distinguish between head nodding and other movements. For example, the feature extraction machine 212 can define characteristic patterns associated with head nodding based on their temporal dynamics. The feature extraction machine 212 can use pattern recognition techniques such as template matching or machine learning classifiers to identify instances of head nodding in the signal.These classifiers can be trained on marked examples of head nodding and non-head nodding movements to improve accuracy and generalizability.

[0043] To detect the direction of the head, the feature extraction machine 212 can, for example, determine the orientation of the driver's head 104 in three-dimensional space based on the video data. This involves analyzing the relative positions of facial features and using geometric calculations to determine the orientation of the head with respect to the video sensor 110.

[0044] In some embodiments, the feature generation machine 214 can combine the extracted audio features and the video features to generate combined features. For example, the combined features can be a concatenation of the audio and video features. The feature generation machine 214 can synchronize the head movements of the driver 104 with the audio data of the driver 104 captured by the audio sensor 112. To perform this synchronization, the combined feature generation machine 214 can perform a temporal alignment, for example, by matching each detected head-nodding event in the video features with the corresponding audio frame or timestamp from the audio features.Temporal alignment algorithms known to the expert can be used to synchronize the head-nodding experiences with the audio signal based on their timestamps, taking into account any latency introduced through the audio processing pipeline to ensure accurate alignment between the head nodding and the singing.

[0045] In some embodiments, the feature generation machine 214 can employ Dynamic Time Warping (DTW) or similar techniques to handle variations in timing and duration between head movements and audio data. DTW allows for flexible matching of sequences with different lengths and temporal distortions and is therefore suitable for matching non-linear patterns in head nods and audio data. This step ensures that the system 114 can correctly interpret the intentions of the driver 104 even if the driver's head movements 104 are not perfectly synchronized with the driver's vocalizations 104.

[0046] In some embodiments, the feature extraction machine 212 can apply a bandpass filter to isolate the frequency range typically associated with blowing sounds (e.g., 500–2000 Hz) and apply noise reduction techniques to enhance the signal for processing audio data. The feature extraction machine 212 can then extract relevant features such as zero-crossing rate, spectral centroid, short-term energy, and Mel-frequency cepstral coefficients (MFCCs). A trained classifier, such as a support vector machine or neural network of the feature extraction machine 212, can distinguish blowing sounds from other sounds. Simultaneously, the feature extraction machine 212 can analyze the video data to detect facial movements associated with the driver 104 blowing air.The feature extraction engine 212 can focus on lip movements, cheek puffing, and changes in facial muscle tension. Computer vision techniques, possibly including deep learning models, can be used by the feature extraction engine 212 to detect these specific gestures related to blowing air. The combined feature generation engine 214 can combine the audio and video data to estimate the intensity of the blowing action. From the audio data, the feature generation engine 214 can analyze the amplitude and duration of the blowing sound. From the video data, the combined feature generation engine 214 can consider the degree of facial movement and mouth opening. This multimodal approach allows for a more reliable estimation of head bobbing, blowing intensity, and similar features.

[0047] In some embodiments, the feature generation machine 214 can perform interpolation and smoothing of the synchronized data to smooth the trajectory of the synchronized head nod, thereby eliminating jitter and improving stability, and use interpolation techniques to fill in missing data points, thus ensuring a continuous representation of the head nod movements. The synchronization algorithm operates in real time and continuously updates the alignment between the head nods and the audio signal as soon as new data becomes available. This real-time adjustment minimizes processing latency and ensures timely feedback and synchronization between the head nods and the singing of the driver 104, which is crucial for providing an intuitive and responsive control mechanism for the rocking parameters of the child seat 106-2.

[0048] In some embodiments, the mapping engine 216 can convert the combined features into vibration parameters for the child seat 106-2. In one example, the rocking parameters can include, but are not limited to, frequency, amplitude, and direction. Each of the rocking parameters can be defined as a set of linear / polynomial equations, with each linear or polynomial equation defined using the audio and / or video features and an appropriate scaling factor. In one example, the mapping engine 216 can calculate the amplitude based on the intensity of the audio data and the size of the detected head bobs to map the combined features to the rocking parameters, as follows: A = k 1·I + k 2·H , where: I is the intensity of the tone, H is the strength of the head nod, k 1 and k 2 are scaling factors.

[0049] In one example, the mapping engine 216 can calculate the frequency based on the rhythm and pitch of the audio data in order to map the combined features to vibration parameters, where the frequency can be given by: f = k3·R + k4·P , where: R is the rhythm of the tone, P is the pitch of the tone, k3 and k4 are scaling factors

[0050] To map the combined features to swing parameters, the mapping engine 216 can, for example, calculate the direction based on the detected head direction, where the direction can be given by: D x=k 5⋅H x Dy = k 6·Hy , where: H x and H y are the x and y components (Cartesian coordinates) of the head direction, and k 5 and k 6 are scaling factors.

[0051] These formulas integrate the extracted features into parameters that control the rocking mechanism of the child car seat 106-2. In some embodiments, the fuzzy inference engine can be configured to convert the audio and video features, represented as definite quantities / values, into fuzzy quantities / values ​​to determine the scaling factors. In some embodiments, the fuzzy inference engine can use a predefined set of membership functions that map any combination of audio and / or video features into fuzzy sets (e.g., low, medium, high, etc. for features such as audio intensity, head bobbing, etc.), which can be further mapped to specific values ​​indicating the "degree of membership" (which can be used as scaling factors).In some embodiments, the fuzzy inference machine can be a Sugeno-type fuzzy inference machine configured to model nonlinear systems with several different linear models, as shown in the example above. In other embodiments, the fuzzy inference machine can be a Mamdani-type fuzzy inference machine.

[0052] In some embodiments, the control unit 218 can actuate the actuators 116 coupled to the child seat 106-2 in order to control the rocking mechanism of the child seat 106-2 based on the rocking parameters. In one example, the control unit 218 can adjust the frequency, amplitude, and / or direction of the rocking motion of the child seat 106-2 based on the calculated rocking parameters in order to control the rocking mechanism.

[0053] In some embodiments, the feature extraction machine 212 can detect the blowing of air and its speed based on the audio and video data, and the control unit 218 can operate an air blower, e.g., a heating, ventilation and air conditioning (HVAC) system of the vehicle 102, accordingly to soothe the infant 106-2.

[0054] In one example, the Mapping Engine 216 can map the detected blowing intensity to the HVAC settings. For instance, a gentle blow might correspond to a low fan speed, while a stronger blow might trigger a higher fan speed. The direction of the airflow can be determined from the video data by analyzing the driver's head position 104 and the direction of the blowing action.

[0055] Based on the detected intensity and direction, the control unit 218 can be connected to the vehicle's HVAC control system 102, e.g. via an electrical means, a bus or other vehicle communication protocols, and adjust the blower speed and use motorized vents to precisely direct the airflow, possibly towards the area of ​​the child seat 106-2.

[0056] In one example, System 114 can install temperature and airflow sensors near the child seat 106-2 to monitor the effectiveness of the directed airflow. System 114 can use this feedback to dynamically adjust the HVAC settings for optimal comfort while implementing safety restrictions to prevent overcooling or excessive airflow. This closed-loop system ensures that the HVAC settings remain appropriate and safe for the comfort of the infant 108.

[0057] In some embodiments, the vehicle 102 may include means for the driver 104 to interact with the system 114, for example, via a human-machine interface (HMI) provided on an instrument cluster or infotainment system of the vehicle 102. For example, if the driver 104 decides to stop singing the lullaby when the infant 108 has fallen asleep, the driver 104 can do so by sending an instruction to the system 114 via the HMI. In some embodiments, a video image of the child seat 106-2 may be displayed on the human-machine interface so that the driver 104 can observe the infant 108 without turning around. The video image may be captured by a camera positioned to provide a clear view of both the child seat 106-2 and the infant 108.This feature enhances safety, as the driver can keep their eyes on the road while simultaneously monitoring the infant's status. The human-machine interface (HMI) can also display real-time information about the currently used rocking parameters, such as frequency, amplitude, and direction of the rocking motion. In addition to visual monitoring, the HMI can provide audio controls, allowing the driver to adjust the volume of a lullaby played through the vehicle's system or switch to a different lullaby or soothing sound. The driver can also use voice commands to interact with the system, enabling hands-free control of the child seat's rocking functions and other related features.

[0058] Fig. Figure 3 shows a flowchart of an example method 300 for controlling the movement of a child seat (e.g., child seat 106-2) in a vehicle 102 according to the embodiments of the present disclosure. In some embodiments, the method 300 can be implemented by a system (such as system 114) in the vehicle 102.

[0059] Referring to Fig. 3. In step 302, the procedure 300 can enable a processor (e.g., processor 202) to receive audio and video data from an occupant. Fig. 2) include. In one example, the occupant could be a driver, such as driver 104, of vehicle 102. In another example, the video data could be received from video sensor 110 and the audio data based on input from audio sensor 112.

[0060] In step 304, the method 300 may include the extraction by the processor 202 of audio features from the audio data and video features from the video data that display gestures. In some embodiments, the audio features may include at least one of the pitch, rhythm, and intensity of the audio data. In some embodiments, the video features may include the detection of head nods and the detection of head direction from the video data. In one example, the detection of head nods may include the detection of the vertical movement of the driver's head 104, and the detection of head direction may include the determination of the orientation of the driver's head 104 in three-dimensional space.

[0061] In step 306, the method 300 may involve the processor 202 determining one or more rocking parameters for a child car seat 106-2 based on the audio and video features using a fuzzy inference engine. In one example, the rocking parameters may include frequency, amplitude, and direction. In some embodiments, the mapping of the combined features to the rocking parameters may include determining the amplitude based on the intensity of the audio data and the size of the detected head bobs, determining the frequency based on the rhythm and pitch of the audio data, and determining the direction based on the detected head direction.In some embodiments, the method 300 may also include synchronizing and combining the audio and video features by the processor 202 to generate combined features, and determining the swing parameters using the combined features.

[0062] In step 308, the method 300 can include the control of a rocking mechanism of the child seat 106-2 by the processor 202 based on the rocking parameters. The rocking mechanism can include actuators / motors and air blower units. In some embodiments, the rocking mechanism can be controlled by adjusting at least one of the parameters—frequency, amplitude, and direction of the rocking motion and / or air blower unit—based on the determined rocking parameters.

[0063] The block diagram in Fig.Figure 4 represents a computer system 400 comprising an external device 410, a bus 420, main memory 430, read-only memory 440, mass storage device 450, a communication port 460, and a processor 470. A person skilled in the art will understand that the system 400 may comprise more than one processor 470 and communication ports 460. The processor 470 may include various modules associated with embodiments of the present disclosure. The communication port 460 may be a recommended standard 232 port for use with a modem-based dial-up connection, a 10 / 100 Ethernet port, a Gigabit or 10 Gigabit port over copper or fiber optic cable, a serial port, a parallel port, or other existing or future ports. The port 460 may be selected according to the network, e.g.,a Local Area Network (LAN), a Wide Area Network (WAN) or any other network to which the System 400 is connected.

[0064] In one embodiment, the memory 430 can be RAM or other dynamic memory generally known in the art. The read-only memory (ROM) 440 can be any static device, e.g., a programmable read-only memory (PROM) for storing static information. The mass storage device 450 can be any current or future mass storage solution that can be used to store information and / or instructions. Examples of mass storage solutions include: Parallel Advanced Technology Attachment (PATA) or Serial Advanced Technology Attachment (SATA) hard disk drives or solid-state drives (internal or external, e.g., with Universal Serial Bus (USB) and / or FireWire interfaces), one or more optical disks, Redundant Array of Independent Disks (RAID) storage, e.g., an array of hard disks (e.g., SATA arrays).

[0065] In one embodiment, bus 420 connects the processor(s) 470 to the other memory, storage, and communication blocks. Bus 420 can be, for example, a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), USB, or similar, to connect expansion cards, drives, and other subsystems, as well as other buses, such as the Front Side Bus (FSB), which connects the processor 470 to the computer system 400.

[0066] In another embodiment, operator and management interfaces, such as a display device, a keyboard, and a cursor control unit, can also be connected to the bus 420 to support direct operator interaction with the computer system 400. Other operator and management interfaces can be provided via network connections connected through the communication port 460. In some embodiments, the external device 410 can be any type of external hard disk drive, floppy disk drive, Compact Disc - Read Only Memory (CD-ROM), Compact Disc - Re-Writable (CD-RW), or Digital Video Disc - Read Only Memory (DVD-ROM). The components described above are given only as examples of various possibilities. The exemplary computer system 400 described above is not intended to limit the scope of this disclosure in any way.

[0067] While the foregoing describes various embodiments of the present disclosure, other and further embodiments of the present disclosure may be developed without departing from the basic scope. The scope of the present disclosure is determined by the following claims. The present disclosure is not limited to the described embodiments, versions, or examples, which are included to enable a person with ordinary technical knowledge to manufacture and use the present disclosure when combined with information and knowledge available to such a person. BENEFITS OF THE PRESENT DISCLOSURE

[0068] The present disclosure provides an interactive and personalized system for rocking a child car seat in a vehicle, increasing the comfort and well-being of both the child and the driver.

[0069] The present disclosure improves childcare during the journey by accurately interpreting the driver's acoustic and visual cues and translating them into appropriate rocking movements for the child seat, without requiring manual input or distracting the driver from driving.

[0070] The present disclosure enhances the calming experience for children in vehicles by automatically adjusting the rocking parameters of the child seat based on real-time sensor data tailored to the individual preferences and behavior of both the driver and the child.

[0071] The present disclosure offers increased adaptability through the integration of advanced feature extraction algorithms and dynamic vibration mechanisms that effectively handle a range of driver inputs, child reactions, and varying vehicle conditions to provide optimal comfort and safety. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] JP 2019034659A

[0006]

Claims

[1] System (114) for controlling a child seat in a vehicle (102) using gestures, comprising: a processor (202); and a memory (204) that is operationally coupled to the processor (202), wherein the memory (204) comprises one or more instructions executable by the processor which, when executed by the processor (202), cause the processor (202) to: To receive audio and video data from an occupant of a vehicle (102); Extracting audio features from the audio data and video features from the video data that display gestures; to determine one or more rocking parameters for a child car seat (106-2) based on the audio features and the video features using a fuzzy inference machine, wherein the one or more rocking parameters include the frequency, the amplitude and the direction; and to control a rocking mechanism of the child seat (106-2) based on one or more rocking parameters. [2] System (114) according to claim 1, wherein the fuzzy inference machine is at least one of the following: Sugeno-type inference machine or Mamdani-type inference machine. [3] System (114) according to claim 1, wherein the processor (202) is further configured to: Synchronizing and combining audio and video features to create combined features; and Determining one or more vibration parameters using the combined characteristics. [4] System (114) according to claim 1, wherein, for determining one or more vibration parameters, the processor (202) is configured to determine one or more corresponding scaling factors for the one or more vibration parameters, and wherein the processor (202) is configured to: to determine one or more scaling factors for the amplitude based on the audio intensity from the audio features and the size of the head nod from the video features; to determine one or more scaling factors for the frequency based on the rhythm and pitch from the audio characteristics; and to determine one or more scaling factors for direction based on the detected head direction from the video features. [5] System (114) according to claim 4, wherein the one or more scaling factors for the one or more rocking parameters are determined on the basis of a predefined membership function that maps a value for the one or more scaling factors to any one or a combination of the audio features and the video features. [6] Method (300) for controlling a child seat in a vehicle (102) using gestures, comprising: Receiving (302) audio and video data of an occupant of a vehicle (102) by a processor (202); Extracting (304) audio features from the audio data and video features from the video data that indicate gestures by the processor (202); Determine (306), by the processor (202), one or more rocking parameters for a child car seat (106-2), based on the audio features and the video features using a fuzzy inference machine, wherein the one or more rocking parameters include frequency, amplitude, and direction; and Control (318) of a rocking mechanism of the child seat (106-2) by the processor (202) on the basis of the rocking parameters. [7] Method (300) according to claim 6, wherein the fuzzy inference machine is at least one of the following: a Sugeno-type inference machine or a Mamdani-type inference machine. [8] Method (300) according to claim 6, wherein the method (300) further comprises: Synchronizing and combining the audio and video features by the processor (202) to produce combined features; and Determination of one or more vibration parameters by the processor (202) using the combined features. [9] Method (300) according to claim 6, wherein the method (300) for determining the one or more vibration parameters comprises determining one or more corresponding scaling factors for the one or more vibration parameters by the processor (202), and wherein the method (300) comprises: Determine, by the processor (202), one or more scaling factors for the amplitude based on the audio intensity from the audio features and the size of the head nod from the video features; Determining one or more scaling factors for the frequency based on the rhythm and pitch from the audio features by the processor (202); and Determine, by the processor (202), one or more scaling factors for direction, based on the detected head direction from the video features. [10] Method (300) according to claim 6, wherein the one or more scaling factors for the one or more rocking parameters are determined on the basis of a predefined membership function that maps a value for the one or more scaling factors to one or a combination of the audio features and the video features.

Images