Apparatus and method for estimating movement of vehicle occupant

Abstract

An apparatus and method for estimating a motion of a vehicle occupant may store a motion estimation model of the vehicle occupant, acquire behavior data of the vehicle, determine a driving mode of the vehicle based on a longitudinal acceleration among the behavior data of the vehicle, and estimate a motion of the vehicle occupant based on the determined driving mode. And estimating a motion of the vehicle occupant using at least one of the motion estimation models corresponding to the driving mode of the vehicle. The motion estimation model may include a first model corresponding to a dynamic mode of the vehicle and a second model corresponding to a steady state mode of the vehicle.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of Korean Patent Application No. 10-2023-0139657, filed on October 18, 2023, which is hereby incorporated by reference into this application. Technical Field

[0003] The present disclosure relates to estimating motion of a vehicle occupant. Background Art

[0004] Motion sickness can usually occur when a person is exposed to one or more specific movements for a long period of time. In this case, factors such as temperature, smell, emotion, and digestion can exacerbate motion sickness.

[0005] Motion sickness occurs when there is a mismatch in input between sensory organs that maintain balance or detect movement and posture (e.g., vision, proprioceptors, semicircular canals, etc.), and can be accompanied by dizziness and vomiting when the user is riding in a vehicle, as the brain becomes temporarily confused.

[0006] In humans, the reactions of sensory organs such as eyes and ears to muscle movements are memorized in the brain. When similar movements occur in the future, the sensory organs predict, prepare, and react to such situations in advance based on the memorized information. However, in a state where the user is riding in a vehicle, because there is no muscle movement due to movement or there is movement different from the previously memorized movement, a mismatch occurs in the senses, and motion sickness occurs.

[0007] As related technologies for predicting motion sickness of vehicle occupants, methods that simply utilize vibration information of the vehicle cannot accurately predict motion sickness of the occupants, and methods that attach sensors to the occupants' bodies can improve prediction accuracy, but the utilization rate is quite low because the attachment of the sensors will cause discomfort to the occupants.

[0008] The contents described in this background technology section are for promoting understanding of the background of the present disclosure and may include contents that are not prior art that is known, available or in use. Summary of the invention

[0009] The present disclosure relates to techniques for estimating the motion (eg, motion of the head) of a vehicle occupant using behavioral data of the vehicle.

[0010] Some embodiments of the present disclosure can solve the above-mentioned problems occurring in the prior art while completely maintaining the advantages achieved by the prior art.

[0011] Embodiments of the present disclosure provide an apparatus and method for estimating the motion of a vehicle occupant, wherein behavior data of the vehicle is collected, the vehicle's driving mode is determined based on the longitudinal acceleration in the vehicle's behavior data, and the motion of the vehicle occupant is estimated based on a model corresponding to the vehicle's driving mode, thereby making it possible to easily and accurately estimate the motion of the vehicle occupant.

[0012] Embodiments of the present disclosure provide an apparatus and method for estimating the motion of a vehicle occupant, wherein a vehicle occupant's motion estimation model based on the vehicle's behavior data traveling in a dynamic mode (hereinafter referred to as a first model) and a vehicle occupant's motion estimation model based on the vehicle's behavior data traveling in a steady-state mode (hereinafter referred to as a second model) are provided, the vehicle's behavior data are collected, the vehicle's driving mode is determined based on the longitudinal acceleration in the vehicle's behavior data, when the vehicle is traveling in the dynamic mode, the vehicle occupant's motion (for example, the vehicle occupant's head motion) is estimated based on the first model, and when the vehicle is traveling in the steady-state mode, the vehicle occupant's motion is estimated based on the second model, thereby making it possible to easily and accurately estimate the vehicle occupant's head motion.

[0013] Embodiments of the present disclosure provide an apparatus and method for estimating the motion of a vehicle occupant, wherein three-axis acceleration, three-axis velocity, roll angle, roll angular rate, pitch angle, and pitch angular rate are collected as behavior data of the vehicle, and the three-axis acceleration of the vehicle occupant's head is collected at the same time. A model for estimating the three-axis acceleration of the vehicle occupant's head in the future is generated based on the vehicle's current behavior data, the current three-axis acceleration of the vehicle occupant's head, and weights. The three-axis acceleration of the vehicle occupant's head is estimated based on the model, so that the motion of the vehicle occupant's head can be easily and accurately estimated.

[0014] Embodiments of the present disclosure provide an apparatus and method for estimating the motion of a vehicle occupant, wherein behavioral data of the vehicle is collected, the driving mode of the vehicle is determined based on the longitudinal acceleration in the behavioral data of the vehicle, a model corresponding to the driving mode of the vehicle is selected, the motion of the vehicle occupant is estimated based on the model, and motion sickness of the vehicle occupant is predicted based on the motion of the vehicle occupant, thereby predicting motion sickness of the vehicle occupant with high accuracy.

[0015] The advantages of some embodiments of the present disclosure are not necessarily limited to the above advantages, and other advantages of some embodiments of the present disclosure that are not described can be understood by the following description and can be more clearly understood by the example embodiments of the present disclosure. Further, it can be apparent that the advantages of some embodiments of the present disclosure can be achieved by the units described in the attached claims and their combinations.

[0016] The technical problems solved by some embodiments of the present disclosure are not necessarily limited to the above-mentioned problems, and through the following description, technical personnel in the field to which the present disclosure belongs can clearly understand the solutions of using the embodiments of the present disclosure to solve other technical problems not mentioned in this document.

[0017] According to an embodiment of the present disclosure, a device for estimating the motion of a vehicle occupant includes: a storage device that stores a motion estimation model of the vehicle occupant; and a controller that collects behavior data of the vehicle, determines the vehicle's driving mode based on the longitudinal acceleration in the vehicle's behavior data, and estimates the motion of the vehicle occupant using a model corresponding to the vehicle's driving mode.

[0018] In an embodiment of the present disclosure, the motion estimation model of the vehicle occupant may be a model that estimates the motion of the vehicle occupant corresponding to the behavior data of the vehicle.

[0019] In an embodiment of the present disclosure, the storage device may store a first model corresponding to a dynamic mode of the vehicle and a second model corresponding to a steady-state mode of the vehicle.

[0020] In an embodiment of the present disclosure, when the longitudinal acceleration deviates from a first threshold range, the controller may estimate the acceleration of the head of the vehicle occupant corresponding to the behavior data of the vehicle based on the first model.

[0021] In an embodiment of the present disclosure, when the longitudinal acceleration does not deviate from the first threshold range and does not deviate from the second threshold range, the controller may estimate the acceleration of the head of the vehicle occupant corresponding to the behavior data of the vehicle based on the second model.

[0022] In an embodiment of the present disclosure, when the longitudinal acceleration does not deviate from the first threshold range and deviates from the second threshold range, the controller may determine a value between the acceleration of the vehicle occupant's head estimated based on the first model and the acceleration of the vehicle occupant's head estimated based on the second model as the acceleration of the vehicle occupant's head.

[0023] In an embodiment of the present disclosure, the controller may collect at least one of three-axis acceleration, three-axis speed, roll angle, roll angle rate, pitch angle, pitch angle rate or any combination thereof as the vehicle behavior data.

[0024] In an embodiment of the present disclosure, the controller may remove noise from the behavior data of the vehicle.

[0025] In an embodiment of the present disclosure, the controller may normalize the behavior data of the vehicle from which noise is removed.

[0026] In an embodiment of the present disclosure, the controller may predict motion sickness of a vehicle occupant based on the vehicle occupant's movements.

[0027] According to an embodiment of the present disclosure, a method for estimating the motion of a vehicle occupant includes: storing a motion estimation model of the vehicle occupant through a storage device; collecting behavior data of the vehicle through a controller; determining a driving mode of the vehicle based on the longitudinal acceleration in the behavior data of the vehicle through the controller; and estimating the motion of the vehicle occupant through the controller using a model corresponding to the driving mode of the vehicle.

[0028] In an embodiment of the present disclosure, storing the motion estimation model of the vehicle occupant may include: storing a first model corresponding to a dynamic mode of the vehicle; and storing a second model corresponding to a steady-state mode of the vehicle.

[0029] In an embodiment of the present disclosure, estimating the movement of a vehicle occupant may include: when the longitudinal acceleration deviates from a first threshold range, estimating, by a controller, the acceleration of the vehicle occupant's head corresponding to the vehicle's behavioral data based on a first model; and when the longitudinal acceleration does not deviate from the first threshold range and does not deviate from the second threshold range, estimating, by a controller, the acceleration of the vehicle occupant's head corresponding to the vehicle's behavioral data based on a second model.

[0030] In an embodiment of the present disclosure, estimating the movement of a vehicle occupant may further include: when the longitudinal acceleration does not deviate from a first threshold range and deviates from a second threshold range, through a controller, determining a value between the acceleration of the vehicle occupant's head estimated based on the first model and the acceleration of the vehicle occupant's head estimated based on the second model as the acceleration of the vehicle occupant's head.

[0031] In an embodiment of the present disclosure, collecting vehicle behavior data may include: through a controller, collecting at least one of three-axis acceleration, three-axis speed, roll angle, roll angle rate, pitch angle, pitch angle rate or any combination thereof as the vehicle behavior data.

[0032] In an embodiment of the present disclosure, collecting the behavior data of the vehicle may further include: removing noise from the behavior data of the vehicle by a controller.

[0033] In an embodiment of the present disclosure, collecting the behavior data of the vehicle may further include: normalizing the behavior data of the vehicle from which noise has been removed, by a controller.

[0034] In an embodiment of the present disclosure, the method may further include: predicting, by the controller, motion sickness of the vehicle occupant based on the movement of the vehicle occupant. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The above and other features and advantages of the present disclosure will become more apparent from the following detailed description in conjunction with the accompanying drawings, in which:

[0036] Figure 1 is a diagram showing an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure;

[0037] Figure 2 is a front view of a vehicle occupant, which shows an attachment position of a human body sensor used in a process of generating a model by a controller provided in the apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure;

[0038] Figure 3 is a table showing a process in which a controller provided in the apparatus for estimating the motion of a vehicle occupant according to an embodiment of the present disclosure determines behavior data of a vehicle to generate a model;

[0039] Figure 4 is a diagram showing a state in which a controller provided in an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure expresses a relationship between behavior data of a vehicle and motion of the occupant using a weight;

[0040] Figure 5 is a diagram showing a model generated by a controller provided in an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure;

[0041] Figure 6 is a graph showing performance of a second model generated by a controller provided in an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure using a data set collected in a steady-state mode;

[0042] Figure 7 is a graph showing performance of a first model generated by a controller provided in an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure using a data set collected in a dynamic mode;

[0043] Figure 8 is a diagram of performance analysis of an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure;

[0044] Fig. 9 is a flow chart illustrating a method for estimating the motion of a vehicle occupant according to an embodiment of the present disclosure; and

[0045] Fig.10 is a block diagram illustrating a computing system for executing a method for estimating motion of a vehicle occupant according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] Hereinafter, some embodiments of the present disclosure will be described in detail with reference to the example drawings. When adding reference numerals to the components of each drawing, it can be noted that the same or equivalent components may be represented by the same reference numerals even when the same or equivalent components are shown on other drawings. Further, when describing the embodiments of the present disclosure, when it is determined that the detailed description of the related known configurations or functions interferes with the understanding of the embodiments of the present disclosure, the detailed description of the related known configurations or functions may be omitted.

[0047] When describing the components of the embodiments of the present disclosure, terms such as "first", "second", "A", "B", "(a)", "(b)", etc. may be used. These terms are intended only to distinguish one component from other components, and these terms do not necessarily limit the nature, order or sequence of the components. Unless otherwise defined, the terms used herein, including technical and scientific terms, may have the same meaning as commonly understood by a person of ordinary skill in the art to which the present disclosure belongs. It may be further understood that terms such as those defined in commonly used dictionaries may be interpreted as having a meaning consistent with their meaning in the context of the relevant art.

[0048] Figure 1 is a diagram illustrating an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure.

[0049] Reference Figure 1 , the apparatus 100 for estimating the motion of a vehicle occupant according to an embodiment of the present disclosure may include a storage device 10, a vehicle network connection device 20, a communication device 30, and a controller 40, any combination or all of which may be multiple or may include multiple components thereof. Depending on the method of implementing the apparatus 100 for estimating the motion of a vehicle occupant according to an embodiment of the present disclosure, the various components may be combined with each other to be implemented as one component, or some components may be omitted.

[0050] In the description of each component, the storage device 10 may be a storage medium that stores various instructions, logics, algorithms, and programs for the following processes: collecting behavior data of the vehicle through a vehicle network, determining a driving mode of the vehicle based on the longitudinal acceleration in the behavior data of the vehicle, and estimating the movement of the vehicle occupants based on a model corresponding to the driving mode of the vehicle.

[0051] The storage device 10 may store a first model that estimates the movement of a vehicle occupant (e.g., movement of the vehicle occupant's head) based on behavior data of the vehicle traveling in a dynamic mode, and a second model that estimates the movement of a vehicle occupant based on behavior data of the vehicle traveling in a steady-state mode.

[0052] The storage device 10 can store various instructions, logics, algorithms and programs for the following processes: collecting vehicle behavior data through a vehicle network, determining the vehicle's driving mode based on the longitudinal acceleration in the vehicle's behavior data, estimating the movement of the vehicle occupant's head based on a first model when the vehicle's driving mode is a dynamic mode, and estimating the movement of the vehicle occupant's head based on a second model when the vehicle's driving mode is a steady-state mode.

[0053] The storage device 10 can store various instructions, logics, algorithms and programs for the following processes: collecting three-axis acceleration, three-axis speed, roll angle, roll angle rate, pitch angle and pitch angle rate as vehicle behavior data through the vehicle network, collecting the three-axis acceleration of the vehicle occupant's head through sensors attached to the vehicle occupant's body, generating a model for estimating the three-axis acceleration of the vehicle occupant's head in the future based on the vehicle's current behavior data, the current three-axis acceleration of the vehicle occupant's head and weights, and estimating the three-axis acceleration of the vehicle occupant's head based on the model.

[0054] The storage device 10 may store various instructions, logics, algorithms and programs for the following processes: collecting behavior data of the vehicle through a vehicle network, determining a driving mode of the vehicle based on the longitudinal acceleration in the behavior data of the vehicle, estimating the movement of a vehicle occupant based on a model corresponding to the driving mode of the vehicle, and predicting motion sickness of the vehicle occupant based on the movement of the vehicle occupant.

[0055] The vehicle network connection device 20 may be a module that provides an interface for accessing a vehicle network, and periodically sends to the vehicle network three-axis (longitudinal, lateral, and vertical) acceleration, three-axis speed, roll angle, roll angle rate, pitch angle, and pitch angle rate that can be measured by various sensors in the vehicle. The vehicle network may include, for example, a controller area network (CAN), a controller area network with flexible data rate (CANFD), a local interconnect network (LIN), FlexRay, a media-oriented system transport (MOST), Ethernet, etc.

[0056] The communication device 30 may be a module that provides a communication interface with the motion sickness prediction server 200, and may transmit the motion data of the vehicle occupant that may be estimated by the controller 40 to the motion sickness prediction server 200, or transmit a message of the controller 40 notifying the possibility of motion sickness of the vehicle occupant to the motion sickness prediction server 200. The communication device 30 may include at least one of a mobile communication module, a wireless Internet module, and a short-range communication module.

[0057] The mobile communication module can communicate with the motion sickness prediction server 200, for example, through a mobile communication network established according to the technical standards or communication methods of mobile communications (for example, Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), Code Division Multiple Access 2000 (CDMA2000), Enhanced Voice Data Optimized or Enhanced Voice Data Dedicated (EV-DO), Wideband CDMA (WCDMA), High Speed ​​Downlink Packet Access (HSDPA), High Speed ​​Uplink Packet Access (HSUPA), Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A)), etc.).

[0058] The wireless Internet module can be a module for wireless Internet access, which can communicate with the motion sickness prediction server 200 through, for example, wireless local area network (WLAN), wireless fidelity (Wi-Fi), Wi-Fi direct, Digital Living Network Alliance (DLNA), wireless broadband (WiBro), world interoperability for microwave access (WiMAX), high-speed downlink packet access (HSDPA), high-speed uplink packet access (HSUPA), long-term evolution (LTE), advanced long-term evolution (LTE-A), etc.

[0059] The short-range communication module can be used, for example, by using Bluetooth TM At least one of , radio frequency identification (RFID), infrared detection and identification (IrDA), ultra-wideband (UWB), ZigBee, near field communication (NFC), and wireless universal serial bus (wireless USB) supports short-range communication with the motion sickness prediction server 200.

[0060] The controller 40 may perform overall control so that each component may perform its function normally. The controller 40 may be implemented in the form of hardware, in the form of software, or in the form of a combination of hardware and software. The controller 40 may include one or more processors. The controller 40 may be implemented as a microprocessor, but the present disclosure is not necessarily limited thereto.

[0061] The controller 40 may collect behavior data of the vehicle through a vehicle network, may determine a driving mode of the vehicle based on the longitudinal acceleration in the behavior data of the vehicle, and may estimate the movement of the vehicle occupants based on a model corresponding to the driving mode of the vehicle.

[0062] When the vehicle's driving mode is a dynamic mode, the controller 40 can estimate the movement of the vehicle occupant's head (e.g., three-axis acceleration) based on a first model stored in the storage device 10, and when the vehicle's driving mode is a steady-state mode, the controller 40 can estimate the movement of the vehicle occupant's head based on a second model.

[0063] Furthermore, the controller 40 may collect three-axis (longitudinal, lateral and vertical) acceleration, three-axis speed, roll angle, roll angle rate, pitch angle and pitch angle rate as vehicle behavior data through the vehicle network.

[0064] In addition, the controller 40 may collect the three-axis acceleration of the head of the vehicle occupant through sensors attached to the occupant's body.

[0065] Further, the controller 40 may generate a model for estimating the three-axis acceleration of the vehicle occupant's head in the future based on the current behavior data of the vehicle, the current three-axis acceleration of the vehicle occupant's head, and the weights.

[0066] In the following, reference will be made to Figures 2 to 5 An example process in which the controller 40 generates a model that estimates the three-axis acceleration of the head of the vehicle occupant is described.

[0067] Figure 2 is a front view of a vehicle occupant illustrating attachment positions of human body sensors used in a process in which a controller provided in an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure generates a model.

[0068] Reference Figure 2 , a triaxial acceleration sensor 210 for measuring the triaxial acceleration of the head of the vehicle occupant may be attached to the head, a triaxial acceleration sensor 220 for measuring the triaxial acceleration of the chest of the vehicle occupant may be attached to the chest of the vehicle occupant, and a triaxial acceleration sensor 230 for measuring the triaxial acceleration of the abdomen of the vehicle occupant may be attached to the abdomen of the vehicle occupant. The triaxial acceleration sensors 210, 220, and 230 may be activated by the controller 40, and may measure the triaxial acceleration of the head, the triaxial acceleration of the chest, and the triaxial acceleration of the abdomen of the vehicle occupant in synchronization with the behavior data of the vehicle under the control of the controller 40. The factor that can have the greatest impact on motion sickness is the head of the vehicle occupant. Therefore, as an example, the process of generating a model using the triaxial acceleration of the head will be described below.

[0069] Figure 3 is a table illustrating a process in which a controller provided in an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure determines behavior data of a vehicle to generate a model.

[0070] Reference Figure 3 , the controller 40 can collect acceleration, speed, roll and pitch as the behavior data of the vehicle that affects the three-axis acceleration of the head, and determine which combination of the behavior data of the vehicle provides the best performance. The controller 40 can use the mean square error (MSE) and the maximum error (ME) for the method of verifying the fitting performance.

[0071] It can be seen that when acceleration and velocity are used, the MSE is 1.3486 and the ME is 3.8143. It can be seen that when acceleration, velocity and roll are used, the MSE is 1.3250 and the ME is 3.8395. It can be seen that when acceleration, velocity and pitch are used, the MSE is 1.3321 and the ME is 3.6560. It can be seen that when all acceleration, velocity, roll and pitch are used, the MSE is 0.5209 and the ME is 2.8498.

[0072] Therefore, when all acceleration, velocity, roll and pitch are used, MSE and ME can be the lowest, so the controller 40 can determine acceleration, velocity, roll and pitch as the behavior data of the vehicle. Acceleration can include three-axis (x-axis, y-axis and z-axis) acceleration, velocity can include three-axis velocity, roll can include roll angle and roll angle rate, and pitch can include pitch angle and pitch angle rate.

[0073] Thereafter, the controller 40 may utilize a filter algorithm such as a Kalman filter, a high pass filter (HPF), and a low pass filter (LPF) to remove noise contained in the three-axis acceleration, three-axis velocity, roll angle, roll angle rate, pitch angle, and pitch angle rate.

[0074] Thereafter, since the scales of the three-axis acceleration, three-axis velocity, roll angle, roll angle rate, pitch angle, and pitch angle rate may be different from each other, the controller 40 may perform a normalization process to adjust the scales to be the same. For example, when the first data is in the range of -2 to 2 and the second data is in the range of -100 to 100, the controller 40 may normalize these ranges to the same range of -1 to 1.

[0075] Thereafter, the controller 40 may generate a column vector “Z” using the three-axis acceleration, three-axis velocity, roll angle, roll angle rate, pitch angle, and pitch angle rate that have been completely normalized as in the following [Equation 1].

[0076] [Equation 1]

[0077]

[0078] In equation 1, represents the three-axis acceleration of the vehicle occupant's head, Represents the vehicle's three-axis acceleration, V xyz represents the three-axis speed, φ represents the roll angle of the vehicle, φ represents the roll rate of the vehicle, θ represents the pitch angle of the vehicle, and Indicates the vehicle's pitch rate.

[0079] Thereafter, the controller 40 may generate a data set matrix for modeling using the column vector "Z" of [Equation 1]. The controller 40 may form i data set matrices from the kth time step to the (k+i-1)th time step as in [Equation 2] below.

[0080] [Equation 2]

[0081]

[0082] Thereafter, the controller 40 may combine [Equation 2] to generate multiple features as in [Equation 3] below.

[0083] [Equation 3]

[0084]

[0085] In Equation 3, the components of multiple features can be expressed as the following [Equation 4]. In this case, it can be expressed up to P 5 , but the present disclosure is not necessarily limited thereto.

[0086] [Equation 4]

[0087]

[0088] In equation 4, represents the square of the acceleration of the head, and It is the product of the acceleration of the head and the speed of the vehicle.

[0089] The multi-features expressed as [Equation 3] and [Equation 4] may include nonlinear elements for expressing the motion of the occupant. Typically, the motion of the occupant may have a nonlinear relationship with the behavior data of the vehicle. Therefore, nonlinear modeling may be used to estimate the motion of the occupant using the behavior data of the vehicle. Therefore, [Equation 3] and [Equation 4] may correspond to data that nonlinearly forms a combination of the behavior data of the vehicle. That is, [Equation 3] and [Equation 4] may be nonlinear models that express the nonlinear relationship between the motion of the occupant and the behavior data of the vehicle.

[0090] Thereafter, the controller 40 may determine the weights of the multiple features using a weight matrix such as the following [Equation 5]. In this case, calculating the weight matrix Ξ may ultimately result in a model for estimating the motion of the occupant. The following [Equation 5] may be as follows Figure 4 The expression shown is used to obtain the weight matrix.

[0091] [Equation 5]

[0092]

[0093] Figure 4is a diagram illustrating a state in which a controller provided in an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure can express a relationship between behavior data of a vehicle and motion of the occupant using a weight.

[0094] exist Figure 4 The target may be the acceleration of the head of the vehicle occupant. Therefore, the controller 40 can use the first column ξ of the weight matrix Ξ 1 To determine the acceleration of the head of the vehicle occupant. In this case, the acceleration of the head of the vehicle occupant may be the acceleration of the head in the vertical direction "z".

[0095] Thereafter, when the controller 40 only Figure 4 Extract the acceleration of the vehicle occupant's head on the left side hour, Figure 4 It can be expressed as the following [Equation 6].

[0096] [Equation 6]

[0097]

[0098] In Equation 6, “ξ 11 ξ 12 ξ 13 …"express Figure 4 The shown 1 The specific weights included in .

[0099] Thereafter, the controller 40 may solve the optimization problem to determine ξ as shown in [Equation 7] below. 1 That is, the controller 40 may determine the ξ that minimizes the cost function “J” 1 .

[0100] [Equation 7]

[0101]

[0102] In Equation 7, in order to estimate the motion of the vehicle occupant using only the behavior data of the vehicle, it is not necessary to use the measured human body data and the weight ξ corresponding thereto. 12 .

[0103] Therefore, the controller 40 may determine the optimal weight matrix by optimizing the cost function using the “internal method” or the “confidence region method” as in the following [Equation 8].

[0104] [Equation 8]

[0105] Ξ * =min Ξ J=min Ξ ‖Z(k+1)-Θ(Z)Ξ‖ 2

[0106] Constraints: ij =0, where i,j and Related

[0107] Thereafter, the controller 40 may calculate the weight matrix * To generate a model for estimating the three-axis acceleration of the vehicle occupant's head. In this case, the optimized weight matrix Ξ * can be a fixed value as a constant. In addition, the model Figure 5 shown.

[0108] Figure 5 is a diagram illustrating a model generated by a controller provided in an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure.

[0109] exist Figure 5 In the left represents the three-axis acceleration of the head of the vehicle occupant to be estimated. and The vehicle behavior data or the combination of vehicle behavior data, and the reference numeral "510" on the right side indicates the vehicle behavior data or the combination of vehicle behavior data. The corresponding weights, and reference numeral "520" indicates In this case, the right side and Human data is included and therefore not used.

[0110] The controller 40 may generate a first model applied when the vehicle's driving mode is a dynamic mode and a second model applied when the vehicle's driving mode is a steady-state mode. Figure 6 and Figure 7 Describe the reason.

[0111] Figure 6 is a graph showing performance of a second model generated by a controller provided in an apparatus for estimating motion of a vehicle occupant using a data set collected in a steady-state mode according to an embodiment of the present disclosure.

[0112] exist Figure 6 , the horizontal axis represents time, and the vertical axis represents x-axis acceleration. Further, reference numeral "610" represents a dynamic driving section where a peak value occurs, reference numeral "620" represents the x-axis acceleration of the occupant's head actually measured, and reference numeral "630" represents the x-axis acceleration of the occupant's head estimated by the second model.

[0113] like Figure 6As shown, it can be seen that the second model based on the data set collected in the steady-state mode of the vehicle may have poor fitting performance in the dynamic driving section 610 where the peak occurs.

[0114] Figure 7 is a graph showing performance of a first model generated by a controller provided in an apparatus for estimating motion of a vehicle occupant using a data set collected in a dynamic mode according to an embodiment of the present disclosure.

[0115] exist Figure 7 , the horizontal axis represents time, and the vertical axis represents x-axis acceleration. Further, reference numeral "710" represents a steady-state driving section, reference numeral "720" represents an x-axis acceleration of the occupant's head actually measured, and reference numeral "730" represents an x-axis acceleration of the occupant's head estimated by the first model.

[0116] like Figure 7 As can be seen, the first model based on the data set acquired in the dynamic mode of the vehicle shows that oscillations may occur in the steady-state driving section.

[0117] Further, when the longitudinal acceleration in the vehicle's behavior data deviates from the first threshold range, the controller 40 can determine the three-axis acceleration of the occupant's head based on the first model, and when the longitudinal acceleration "a" does not deviate from the first threshold range (for example, -2<a<2) and does not deviate from the second threshold range (for example, -1<a<1), the controller 40 can determine the three-axis acceleration of the occupant's head based on the second model.

[0118] When the longitudinal acceleration "a" does not deviate from the first threshold range (e.g., -2 < a < 2) and deviates from the second threshold range (e.g., -1 < a < 1), the controller 40 can finally determine the three-axis acceleration of the occupant's head by multiplying the three-axis acceleration of the occupant's head based on the first model and the three-axis acceleration of the occupant's head based on the second model by a certain ratio. In this case, the controller 40 can apply an interpolation method. For example, when the three-axis acceleration of the occupant's head based on the first model is 3, and the three-axis acceleration of the occupant's head based on the second model is 2, 2.5 can be determined as the final three-axis acceleration of the occupant's head.

[0119] Figure 8 is a diagram of performance analysis of an apparatus for estimating motion of a vehicle occupant according to an embodiment of the present disclosure.

[0120] exist Figure 8, the horizontal axis represents time, and the vertical axis represents the acceleration of the head in the vertical direction (z-axis). In addition, the solid line 810 represents the actual measured acceleration of the head in the vertical direction, and the dotted line 820 represents the acceleration of the head in the vertical direction estimated by the apparatus for estimating the motion of the vehicle occupant according to an embodiment of the present disclosure.

[0121] like Figure 8 As shown, the solid line 810 and the dotted line 820 are almost the same, so it can be seen that the estimation performance of the apparatus for estimating the motion of the vehicle occupant according to the embodiment of the present disclosure is very excellent.

[0122] In addition, the controller 40 can directly predict the motion sickness of the vehicle occupant based on the three-axis acceleration of the head of the vehicle occupant. For example, when at least one of the longitudinal acceleration, lateral acceleration, and vertical acceleration of the head of the vehicle occupant is greater than a threshold value and the number of times the acceleration is greater than the threshold value is greater than a preset number of times, it can be predicted that the occupant suffers from motion sickness.

[0123] Fig. 9 is a flow chart illustrating a method for estimating motion of a vehicle occupant according to an embodiment of the present disclosure.

[0124] In operation 901 , the storage device 10 may store a motion estimation model of a vehicle occupant.

[0125] In operation 902 , the controller 40 may collect behavior data of the vehicle through a vehicle network.

[0126] In operation 903 , the controller 40 may determine a driving mode of the vehicle based on the longitudinal acceleration among the behavior data of the vehicle.

[0127] In operation 904 , the controller 40 may estimate the motion of the vehicle occupant using a model corresponding to the driving mode of the vehicle.

[0128] Fig.10 is a block diagram illustrating a computing system for executing a method for estimating motion of a vehicle occupant according to an embodiment of the present disclosure.

[0129] Reference Fig.10, the method for estimating the motion of the vehicle occupant according to the embodiment of the present disclosure may also be implemented by the computing system 1000. The computing system 1000 may include at least one processor 1100, a memory 1300, a user interface input device 1400, a user interface output device 1500, a storage device 1600, and a network interface 1700 connected via a system bus 1200, and any combination or all of the at least one processor 1100, the memory 1300, the user interface input device 1400, the user interface output device 1500, the storage device 1600, and the network interface 1700 connected via the system bus 1200 may be multiple or may include multiple components thereof.

[0130] The processor 1100 may be a central processing unit (CPU) or a semiconductor device that processes commands stored in the memory 1300 and / or the storage device 1600. The storage medium may include the memory 1300 and the storage device 1600, and may include various types of volatile or non-volatile storage media. For example, the memory 1300 may include a read-only memory (ROM) 1310 and a random access memory (RAM) 1320.

[0131] Therefore, the operation of the method or algorithm described in conjunction with some embodiments disclosed herein can be implemented directly in hardware, software modules, or a combination of both components run by the processor 1100. The software module may reside in a storage medium (i.e., memory 1300 and / or storage device 1600) such as RAM, flash memory, ROM, erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), registers, hard disks, removable disks, and compact disks (CD)-ROMs. An example storage medium may be coupled to the processor 1100, and the processor 1100 may read information from the storage medium and write information to the storage medium. In another method, the storage medium may be integrated with the processor 1100. The processor 1100 and the storage medium may reside in an application specific integrated circuit (ASIC). The ASIC may reside in a user terminal. In another method, the processor 1100 and the storage medium may reside in a user terminal as separate components.

[0132] According to an embodiment of the present disclosure, vehicle behavior data can be collected, the vehicle's driving mode can be determined based on the longitudinal acceleration in the vehicle's behavior data, a model corresponding to the vehicle's driving mode can be selected, and the movement of the vehicle's occupants can be estimated based on the model, so the movement of the vehicle's occupants can be easily and accurately estimated.

[0133] The above description is only an illustration of the technical spirit of the present disclosure, and a person skilled in the art to which the present disclosure belongs can make various modifications and changes without departing from the features of the present disclosure. Therefore, the exemplary embodiments disclosed in the present disclosure are not intended to limit the technical spirit of the present disclosure, but are intended to describe the present disclosure, and the scope of the technical spirit of the present disclosure is not necessarily limited by these embodiments. The scope of protection of the present disclosure can be interpreted by the attached claims, and all technical spirits within the scope equivalent thereto can be interpreted as included within the scope of the present disclosure.

Claims

1. An apparatus for estimating the motion of a vehicle occupant, comprising: one or more processors; A non-transitory storage medium storing a motion estimation model of the vehicle occupant and computer-readable instructions, wherein the instructions, when executed by the one or more processors, enable the one or more processors to: collect behavior data of the vehicle, determine the driving mode of the vehicle based on the longitudinal acceleration in the behavior data of the vehicle, and estimate the motion of the vehicle occupant using at least one motion estimation model in the motion estimation model corresponding to the driving mode of the vehicle.

2. The device according to claim 1, wherein: At least one of the vehicle occupant motion estimation models estimates motion of the vehicle occupant corresponding to behavior data of the vehicle.

3. The device according to claim 1, wherein: The motion estimation model includes a first model corresponding to a dynamic mode of the vehicle and a second model corresponding to a steady-state mode of the vehicle.

4. The device according to claim 3, wherein: The instructions further cause the one or more processors to: If the longitudinal acceleration deviates from a first threshold range, estimating an acceleration of the head of the vehicle occupant corresponding to the behavior data of the vehicle based on the first model, and If the longitudinal acceleration is within the first threshold range and within a second threshold range, an acceleration of the head of the vehicle occupant corresponding to the behavior data of the vehicle is estimated based on the second model.

5. The device according to claim 4, wherein: The instructions further cause the one or more processors to: If the longitudinal acceleration is within the first threshold range and deviates from the second threshold range, it is determined that the acceleration of the vehicle occupant's head is a value between a first acceleration of the vehicle occupant's head estimated based on the first model and a second acceleration of the vehicle occupant's head estimated based on the second model.

6. The device according to claim 3, wherein: The instructions further cause the one or more processors to: One or any combination of three-axis acceleration, three-axis speed, roll angle, roll angle rate, pitch angle and pitch angle rate is collected as the behavior data of the vehicle.

7. The device according to claim 6, wherein: The instructions further cause the one or more processors to: Noise is removed from the behavior data of the vehicle.

8. The device according to claim 7, wherein: The instructions further cause the one or more processors to: The behavior data of the vehicle from which the noise is removed is normalized.

9. The device according to claim 1, wherein: The instructions further cause the one or more processors to: Motion sickness of the vehicle occupant is predicted based on the movement of the vehicle occupant.

10. A method for estimating the motion of a vehicle occupant, comprising: storing a motion estimation model of the vehicle occupant; Collect vehicle behavior data; determining a driving mode of the vehicle based on the longitudinal acceleration among the behavior data of the vehicle; as well as The motion of the vehicle occupant is estimated using at least one of the motion estimation models that corresponds to the driving mode of the vehicle.

11. The method according to claim 10, wherein: At least one of the vehicle occupant motion estimation models estimates motion of the vehicle occupant corresponding to behavior data of the vehicle.

12. The method according to claim 10, wherein: Storing the motion estimation model of the vehicle occupant includes: storing a first model corresponding to a dynamic mode of the vehicle; and A second model corresponding to a steady-state mode of the vehicle is stored.

13. The method according to claim 12, wherein: Estimating the motion of the vehicle occupant includes: If the longitudinal acceleration deviates from a first threshold range, estimating an acceleration of the head of the vehicle occupant corresponding to the behavior data of the vehicle based on the first model; and If the longitudinal acceleration is within the first threshold range and within a second threshold range, an acceleration of the head of the vehicle occupant corresponding to the behavior data of the vehicle is estimated based on the second model.

14. The method according to claim 13, wherein: Estimating the motion of the vehicle occupant further comprises: If the longitudinal acceleration is within the first threshold range and deviates from the second threshold range, it is determined that the acceleration of the vehicle occupant's head is a value between a first acceleration of the vehicle occupant's head estimated based on the first model and a second acceleration of the vehicle occupant's head estimated based on the second model.

15. The method according to claim 12, wherein: The collected vehicle behavior data includes: One or any combination of three-axis acceleration, three-axis speed, roll angle, roll angle rate, pitch angle and pitch angle rate is collected as the behavior data of the vehicle.

16. The method according to claim 15, wherein: The collected vehicle behavior data further includes: Noise is removed from the behavior data of the vehicle.

17. The method according to claim 16, wherein: The collected vehicle behavior data further includes: The behavior data of the vehicle from which the noise is removed is normalized.

18. The method according to claim 10, further comprising: Motion sickness of the vehicle occupant is predicted based on the movement of the vehicle occupant.

Images