Method and device for determining head movement track of driver, vehicle and storage medium

Abstract

The invention relates to the technical field of vehicles, in particular to a method and device for determining the head motion trail of a driver, a vehicle and a storage medium. Under the condition that the vehicle collides, the current seat backrest angle, the current collision form and the current collision speed of the vehicle are obtained; the current seat backrest angle, the current collision form and the current collision speed are input into a preset head trajectory prediction model to obtain a head movement trajectory of the driver, and the preset head trajectory prediction model is obtained by constructing a preset neural network through matrix processing results of the multiple collision parameters. Therefore, the problems that when a large-angle seat is collided, the head movement track of the driver is complex, the head position of the driver is difficult to accurately predict, and the optimization design of a large-angle seat air bag system cannot be effectively supported are solved, and through high-density working condition simulation, the head track prediction accuracy under the complex working condition is improved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicles, and particularly to a method, device, vehicle and storage medium for determining the movement trajectory of a driver's head. Background Art

[0002] Parameters such as the position definition of the airbag, the deployment pattern, and the ignition time need to be determined according to the head position of the driver during a collision.

[0003] [[ID=NO=11]]In the related art, a large number of cameras are arranged in the vehicle to locate the head position of the driver according to the pixelated image. However, the related art has the following problems: (1) Complex installation and high cost: The camera layout is restricted by the vehicle space and may not be adaptable to different vehicle models or seat configurations; (2) The positioning method based on image recognition is vulnerable to factors such as illumination and occlusion, and the accuracy is limited; (3) The related art is mainly designed for conventional seat angles and is difficult to meet the special requirements of large-angle seats: The movement trajectory of the occupant during a collision of a large-angle seat is complex, and it is difficult to accurately predict the head position; It cannot effectively support the optimization design of the airbag system for large-angle seats (such as position, deployment pattern, ignition moment); (4) Laboratory tests or real vehicle collision tests are limited by the number of working condition combinations and it is difficult to exhaust all possible collision scenarios, resulting in insufficient robustness of the airbag design parameters. Summary of the Invention

[0004] The present application provides a method, device, vehicle and storage medium for determining the movement trajectory of a driver's head to solve the problem that the movement trajectory of the driver's head during a collision of a large-angle seat is complex, it is difficult to accurately predict the head position of the driver, and it cannot effectively support the optimization design of the airbag system for large-angle seats. Through high-density working condition simulation, the accuracy of head trajectory prediction under complex working conditions is improved, and no additional hardware devices need to be deployed, reducing the R & D cost.

[0005] The first aspect of the present application provides a method for determining the movement trajectory of a driver's head, including the following steps:

[0006] Judge whether the vehicle has a collision;

[0007] In the case that the vehicle has a collision, obtain the current seat backrest angle, the current collision form and the current collision speed of the vehicle;

[0008] Input the current seat backrest angle, the current collision form and the current collision speed into a preset head trajectory prediction model to obtain the movement trajectory of the driver's head, where the preset head trajectory prediction model is constructed by matrix processing results of multiple collision parameters for a preset neural network.

[0009] Optionally, in some embodiments, before inputting the angle of the vehicle seat, the current collision form, and the current collision speed into a preset head trajectory prediction model to obtain the head position of the driver, it includes:

[0010] Determine a plurality of collision parameters, where the plurality of collision parameters include a plurality of seat back angles, a plurality of collision forms, and a plurality of collision speeds;

[0011] Respectively perform matrix processing on the plurality of seat back angles, the plurality of collision forms, and the plurality of collision speeds, and obtain a head movement trajectory matrix according to the matrix processing results;

[0012] Establish the preset head trajectory prediction model according to the matrix processing results and the head movement trajectory matrix.

[0013] Optionally, in some embodiments, the respectively performing matrix processing on the plurality of seat back angles, the plurality of collision forms, and the plurality of collision speeds, and obtaining a head movement trajectory matrix according to the matrix processing results includes:

[0014] Perform matrix processing on the plurality of seat back angles, the plurality of collision forms, and the plurality of collision speeds to obtain a seat back angle matrix, a collision form matrix, and a collision speed matrix;

[0015] Determine a plurality of test combinations according to the seat back angle matrix, the collision form matrix, and the collision speed matrix, and perform simulation on each test combination to obtain the head movement trajectory matrix.

[0016] Optionally, in some embodiments, the establishing the preset head trajectory prediction model according to the matrix processing results and the head movement trajectory matrix includes:

[0017] Establish an initial matrix combination relationship according to the seat back angle matrix, the collision form matrix, the collision speed matrix, and the head movement trajectory matrix;

[0018] Perform unitization processing on the initial matrix combination relationship to obtain a unitized matrix combination relationship, and sample the processed matrix combination relationship to obtain the corresponding relationship between the unit condition matrix and the unit result matrix;

[0019] Based on the corresponding relationship between the unit condition matrix and the unit result matrix, construct the preset neural network to obtain the preset head trajectory prediction model.

[0020] Optionally, in some embodiments, after obtaining the head movement trajectory of the driver, it includes:

[0021] Determine the concentrated area of the driver's head movement trajectory, and determine the deployment parameters of the airbag according to the concentrated area.

[0022] Optionally, in some embodiments, the collision form includes at least one of: full-width frontal rigid collision, frontal offset rigid collision, frontal deformable barrier collision, and oblique frontal collision.

[0023] An embodiment of the second aspect of the present application provides a device for determining the driver's head movement trajectory, including:

[0024] A judgment module, configured to judge whether a vehicle collision occurs;

[0025] An acquisition module, configured to acquire the current seat backrest angle, the current collision form, and the current collision speed of the vehicle when the vehicle collides;

[0026] A generation module, configured to input the current seat backrest angle, the current collision form, and the current collision speed into a preset head trajectory prediction model to obtain the driver's head movement trajectory, where the preset head trajectory prediction model is constructed by matrix processing results of multiple collision parameters for a preset neural network.

[0027] Optionally, in some embodiments, before inputting the angle of the vehicle seat, the current collision form, and the current collision speed into a preset head trajectory prediction model to obtain the driver's head position, the generation module includes:

[0028] A first determination unit, configured to determine multiple collision parameters, where the multiple collision parameters include multiple seat backrest angles, multiple collision forms, and multiple collision speeds;

[0029] A processing unit, configured to respectively perform matrix processing on the multiple seat backrest angles, the multiple collision forms, and the multiple collision speeds, and obtain a head movement trajectory matrix according to the matrix processing results;

[0030] An establishment unit, configured to establish the preset head trajectory prediction model according to the matrix processing results and the head movement trajectory matrix.

[0031] Optionally, in some embodiments, the processing unit includes:

[0032] A processing subunit, configured to perform matrix processing on the multiple seat backrest angles, the multiple collision forms, and the multiple collision speeds to obtain a seat backrest angle matrix, a collision form matrix, and a collision speed matrix;

[0033] A simulation sub-unit, configured to determine a plurality of test combinations according to a seat back angle matrix, a collision form matrix, and a collision speed matrix, and perform simulations on each test combination to obtain the head movement trajectory matrix.

[0034] Optionally, in some embodiments, the establishing unit includes:

[0035] An establishing sub-unit, configured to establish an initial matrix combination relationship according to a seat back angle matrix, a collision form matrix, a collision speed matrix, and a head movement trajectory matrix;

[0036] A sampling sub-unit, configured to perform unitarization processing on the initial matrix combination relationship to obtain a unitarized matrix combination relationship, and sample the processed matrix combination relationship to obtain the correspondence between the unit condition matrix and the unit result matrix;

[0037] A constructing sub-unit, configured to construct the preset neural network based on the correspondence between the unit condition matrix and the unit result matrix to obtain the preset head trajectory prediction model.

[0038] Optionally, in some embodiments, after obtaining the head movement trajectory of the driver, the generating module includes:

[0039] A second determining unit, configured to determine the concentration area of the head movement trajectory of the driver, and determine the deployment parameters of the airbag according to the concentration area.

[0040] Optionally, in some embodiments, the collision form includes at least one of full-width frontal rigid collision, frontal offset rigid collision, frontal deformable barrier collision, and oblique frontal collision.

[0041] An embodiment of the third aspect of the present application provides a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the method for determining the head movement trajectory of the driver as described in the above embodiments.

[0042] An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and the program is executed by a processor to be used to implement the method for determining the head movement trajectory of the driver as described in the above embodiments.

[0043] Thus, by determining whether a vehicle collision has occurred, in the case of a vehicle collision, the current seat back angle, the current collision form, and the current collision speed of the vehicle are obtained, and the current seat back angle, the current collision form, and the current collision speed are input into a preset head trajectory prediction model to obtain the head movement trajectory of the driver. Among them, the preset head trajectory prediction model is constructed by matrix processing results of multiple collision parameters for a preset neural network. Thus, the problem that the head movement trajectory of the driver is complex during a collision of a large-angle seat, it is difficult to accurately predict the head position of the driver, and it is impossible to effectively support the optimization design of the large-angle seat airbag system is solved. Through high-density working condition simulation, the accuracy of head trajectory prediction under complex working conditions is improved.

[0044] Additional aspects and advantages of the present application will be given in part in the following description, will become apparent in part from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0046] Figure 1 is a flowchart of a method for determining a head movement trajectory of a driver according to an embodiment of the present application;

[0047] Figure 2 is a block diagram of a device for determining a head movement trajectory of a driver according to an embodiment of the present application;

[0048] Figure 3 is a structural diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0050] The method, device, vehicle, and storage medium for determining the driver's head movement trajectory according to the embodiments of the present application will be described below with reference to the accompanying drawings. In view of the problem mentioned in the above background art that the movement trajectory of the driver's head is complex during a collision of a large-angle seat, it is difficult to accurately predict the position of the driver's head, and it is impossible to effectively support the optimization design of the large-angle seat airbag system, the present application provides a method for determining the driver's head movement trajectory. In this method, by determining whether the vehicle has a collision, in the case of a vehicle collision, the current seat backrest angle, the current collision form, and the current collision speed of the vehicle are obtained, and the current seat backrest angle, the current collision form, and the current collision speed are input into a preset head trajectory prediction model to obtain the driver's head movement trajectory, where the preset head trajectory prediction model is constructed by matrix processing results of multiple collision parameters for a preset neural network. Thus, the problem that the movement trajectory of the driver's head is complex during a collision of a large-angle seat, it is difficult to accurately predict the position of the driver's head, and it is impossible to effectively support the optimization design of the large-angle seat airbag system is solved, and the accuracy of head trajectory prediction under complex working conditions is improved through high-density working condition simulation.

[0051] Specifically, Figure 1 FIG. is a schematic flowchart of a method for determining the driver's head movement trajectory provided by an embodiment of the present application.

[0052] As Figure 1 shown, the method for determining the driver's head movement trajectory includes the following steps:

[0053] In step S101, it is determined whether the vehicle has a collision.

[0054] Specifically, in the embodiment of the present application, it can be determined whether the vehicle has a collision through a collision sensor. For example, when the vehicle is impacted, the collision sensor will detect a sudden change in acceleration or deceleration and transmit a signal to the vehicle control system, and then determine whether the vehicle has a collision.

[0055] In step S102, in the case of a vehicle collision, the current seat backrest angle, the current collision form, and the current collision speed of the vehicle are obtained.

[0056] Among them, the current collision form includes at least one of full-width frontal rigid collision, frontal offset rigid collision, frontal deformable barrier collision, and oblique frontal collision.

[0057] Specifically, in the embodiment of the present application, the collision state of the vehicle is analyzed through various parameters such as the current seat backrest angle, the current collision form, and the current collision speed, covering various working conditions such as full-width frontal collision, offset collision, and deformable barrier collision.

[0058] In step S103, the current seat back angle, the current collision form, and the current collision speed are input into a preset head trajectory prediction model to obtain the head movement trajectory of the driver, where the preset head trajectory prediction model is constructed by matrix processing results of multiple collision parameters for a preset neural network.

[0059] Further, in some embodiments, after obtaining the head movement trajectory of the driver, it includes: determining the concentration area of the head movement trajectory of the driver, and determining the deployment parameters of the airbag according to the concentration area.

[0060] Specifically, in the embodiments of the present application, by inputting the collision parameters of the vehicle (such as seat back angle, collision form, and collision speed, etc.), the movement trajectory of the driver's head is predicted, the head movement trajectory is analyzed, the concentration area of the head movement is determined, that is, the position where the head is most likely to reach during the collision, and according to the concentration area, the deployment parameters of the airbag are adjusted, such as deployment angle, deployment speed, and inflation pressure, etc. The optimization of these parameters aims to enable the airbag to more effectively protect the driver's head when the collision occurs.

[0061] Further, in some embodiments, before inputting the angle of the vehicle seat, the current collision form, and the current collision speed into the preset head trajectory prediction model to obtain the head position of the driver, it includes: determining multiple collision parameters, where the multiple collision parameters include multiple seat back angles, multiple collision forms, and multiple collision speeds; respectively performing matrix processing on the multiple seat back angles, multiple collision forms, and multiple collision speeds, and obtaining a head movement trajectory matrix according to the matrix processing results; establishing a preset head trajectory prediction model according to the matrix processing results and the head movement trajectory matrix.

[0062] Specifically, the embodiments of the present application define different backrest angle positions of a large-angle seat as P1, P2, P3,..., PN respectively; define different frontal collision forms as full-width frontal rigid collision C1, frontal offset rigid collision C2, frontal deformable barrier collision C3, oblique frontal collision C4,..., CM, etc.; define different collision speeds as S1, S2, S3, S4, S5, S6,..., SI respectively. Through simulation calculations on a large-angle seat at a certain position of a certain vehicle model, according to the input conditions: different backrest angle positions PN, different frontal collision forms CM, different collision speeds SI, different occupant head movement trajectories T1, T2, T3,..., TT can be obtained through simulation calculations.

[0063] It should be noted that more refined inputs can be made for the simulation conditions. For example, the backrest angle can be input under the condition of increasing by 1 degree, and the result data is larger and more accurate. In addition, for the input simulation conditions, in addition to the backrest angle, collision form, and collision speed, it can also include, as collision parameters, seat cushion materials, seat forms, seat belt positions, etc. The more input conditions there are, the better the stability of the test and the better the protection effect on the occupants.

[0064] Optionally, in some embodiments, matrix processing is respectively performed on a plurality of seat backrest angles, a plurality of collision forms, and a plurality of collision speeds, and a head movement trajectory matrix is obtained according to the matrix processing result, including: performing matrix processing on a plurality of seat backrest angles, a plurality of collision forms, and a plurality of collision speeds to obtain a seat backrest angle matrix, a collision form matrix, and a collision speed matrix; determining a plurality of test combinations according to the seat backrest angle matrix, the collision form matrix, and the collision speed matrix, and performing simulation on each test combination to obtain a head movement trajectory matrix.

[0065] Specifically, in the embodiment of the present application, through the one-to-one combination of the backrest angle P matrix, the collision form C matrix, and the collision speed S matrix, the final result, the occupant head movement trajectory T matrix, can be obtained through computer simulation, as shown in the following formula:

[0066]

[0067] Optionally, in some embodiments, a preset head trajectory prediction model is established according to the matrix processing result and the head movement trajectory matrix, including: establishing an initial matrix combination relationship according to the seat backrest angle matrix, the collision form matrix, the collision speed matrix, and the head movement trajectory matrix; performing unitarization processing on the initial matrix combination relationship to obtain a unitarized matrix combination relationship, and sampling the processed matrix combination relationship to obtain the corresponding relationship between the unit condition matrix and the unit result matrix; based on the corresponding relationship between the unit condition matrix and the unit result matrix, constructing a preset neural network to obtain a preset head trajectory prediction model.

[0068] Specifically, unitarization processing is respectively performed on the backrest angle P matrix, the collision form C matrix, the collision speed S matrix, and the occupant head movement trajectory T matrix, and finally the following matrix combination relationship can be obtained:

[0069]

[0070] In the embodiments of the present application, a large number of unitized conditional matrices, namely, unitized backrest angle P matrix, unitized collision form C matrix, unitized collision speed S matrix, unitized result matrix Q matrix, and unitized occupant head movement trajectory T matrix, are obtained by performing Latin hypercube sampling on each matrix. There is a relationship between the unitized conditional U matrix and the unitized result Q matrix, and they can be connected according to the neural network relationship as follows:

[0071]

[0072] In the embodiments of the present application, based on the one-to-one correspondence between the above-mentioned unitized conditional U matrix and the unitized result Q matrix, a preset head trajectory prediction model is constructed for the preset neural network, as shown in the following formula:

[0073]

[0074] In the embodiments of the present application, through a large number of simulation calculations, the position of the occupant's head during different collision processes is determined, which is beneficial to the passive safety protection of large-angle seats. In addition, in the simulation results, the head movement trajectory will be concentrated in a certain area, and this area is the contact position between the occupant's head and the airbag for the large-angle seat at this position of this vehicle model. Based on the determination of the position, the position of the airbag is defined, the deployment pattern is determined, the ignition time is calibrated, etc., as a design reference for the airbag restraint system.

[0075] Therefore, by performing simulation calculations on different backrest angles of large-angle seats at different collision speeds under different frontal collision forms, specific occupant head movement trajectory results can be obtained, providing data support for the position, deployment pattern, and ignition time parameters of the airbag restraint system, and solving the development problem of the airbag restraint system for large-angle seats.

[0076] According to the method for determining the driver's head movement trajectory proposed in the embodiments of the present application, by determining whether the vehicle has collided, in the case of a vehicle collision, the current seat backrest angle, the current collision form, and the current collision speed of the vehicle are obtained, and the current seat backrest angle, the current collision form, and the current collision speed are input into a preset head trajectory prediction model to obtain the driver's head movement trajectory. Among them, the preset head trajectory prediction model is constructed by matrix processing results of multiple collision parameters for a preset neural network. Thus, the problem that the driver's head movement trajectory is complex during a collision of a large-angle seat, it is difficult to accurately predict the driver's head position, and it is impossible to effectively support the optimization design of the airbag system for large-angle seats is solved, and the accuracy of head trajectory prediction under complex working conditions is improved through high-density working condition simulation.

[0077] Next, a device for determining the driver's head movement trajectory according to the embodiments of the present application is described with reference to the accompanying drawings.

[0078] Figure 2 It is a block diagram of a device for determining the head movement trajectory of an embodiment of the present application.

[0079] As Figure 2 shown, the device 10 for determining the head movement trajectory of the driver includes: a judgment module 100, an acquisition module 200, and a generation module 300.

[0080] Among them, the judgment module 100 is used to judge whether the vehicle has a collision.

[0081] The acquisition module 200 is used to acquire the current seat back angle, the current collision form, and the current collision speed of the vehicle in the case of a vehicle collision.

[0082] The generation module 300 is used to input the current seat back angle, the current collision form, and the current collision speed into a preset head trajectory prediction model to obtain the head movement trajectory of the driver. Among them, the preset head trajectory prediction model is constructed by matrix processing results of multiple collision parameters for a preset neural network.

[0083] Optionally, in some embodiments, before inputting the angle of the vehicle seat, the current collision form, and the current collision speed into the preset head trajectory prediction model to obtain the head position of the driver, the generation module 300 includes: a first determination unit, a processing unit, and a building unit.

[0084] Among them, the first determination unit is used to determine multiple collision parameters, where the multiple collision parameters include multiple seat back angles, multiple collision forms, and multiple collision speeds.

[0085] The processing unit is used to perform matrix processing on multiple seat back angles, multiple collision forms, and multiple collision speeds respectively, and obtain a head movement trajectory matrix according to the matrix processing results.

[0086] The building unit is used to establish a preset head trajectory prediction model according to the matrix processing results and the head movement trajectory matrix.

[0087] Optionally, in some embodiments, the processing unit includes: a processing subunit and a simulation subunit.

[0088] Among them, the processing subunit is used to perform matrix processing on multiple seat back angles, multiple collision forms, and multiple collision speeds to obtain a seat back angle matrix, a collision form matrix, and a collision speed matrix;

[0089] The simulation subunit is used to determine multiple test combinations according to the seat back angle matrix, the collision form matrix, and the collision speed matrix, and perform simulations on each test combination to obtain a head movement trajectory matrix.

[0090] Optionally, in some embodiments, the establishment unit includes: an establishment subunit, a sampling subunit, and a construction subunit.

[0091] Among them, the establishment subunit is used to establish an initial matrix combination relationship according to the seat back angle matrix, the collision form matrix, the collision speed matrix, and the head movement trajectory matrix.

[0092] The sampling subunit is used to perform unitary processing on the initial matrix combination relationship to obtain a unitary matrix combination relationship, and sample the processed matrix combination relationship to obtain the corresponding relationship between the unit condition matrix and the unit result matrix.

[0093] The construction subunit is used to construct a preset neural network based on the corresponding relationship between the unit condition matrix and the unit result matrix to obtain a preset head trajectory prediction model.

[0094] Optionally, in some embodiments, after obtaining the driver's head movement trajectory, the generation module 300 includes: a second determination unit.

[0095] Among them, the second determination unit is used to determine the concentrated area of the driver's head movement trajectory and determine the deployment parameters of the airbag according to the concentrated area.

[0096] Optionally, in some embodiments, the collision form includes at least one of full-width frontal rigid collision, frontal offset rigid collision, frontal deformable barrier collision, and oblique frontal collision.

[0097] It should be noted that the foregoing explanation of the embodiments of the method for determining the driver's head movement trajectory also applies to the device for determining the driver's head movement trajectory in this embodiment, and will not be repeated here.

[0098] According to the device for determining the driver's head movement trajectory provided by the embodiments of the present application, by determining whether the vehicle has a collision, in the case of a vehicle collision, the current seat back angle, the current collision form, and the current collision speed of the vehicle are obtained, and the current seat back angle, the current collision form, and the current collision speed are input into a preset head trajectory prediction model to obtain the driver's head movement trajectory, where the preset head trajectory prediction model is constructed by matrix processing results of multiple collision parameters for a preset neural network. Thus, the problem that the driver's head movement trajectory is complex during a collision of a large-angle seat, it is difficult to accurately predict the driver's head position, and it is impossible to effectively support the optimization design of the large-angle seat airbag system is solved, and the accuracy of head trajectory prediction under complex working conditions is improved through high-density working condition simulation.

[0099] Figure 3 The structural schematic diagram of the vehicle provided by the embodiments of the present application. The vehicle may include:

[0100] A memory 301, a processor 302, and a computer program stored on the memory 301 and executable on the processor 302.

[0101] When the processor 302 executes the program, it implements the method for determining the driving head movement trajectory provided in the above embodiments.

[0102] Furthermore, the vehicle further includes:

[0103] A communication interface 303 for communication between the memory 301 and the processor 302.

[0104] The memory 301 is used to store a computer program executable on the processor 302.

[0105] The memory 301 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0106] If the memory 301, the processor 302, and the communication interface 303 are independently implemented, the communication interface 303, the memory 301, and the processor 302 can be interconnected through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0107] Optionally, in specific implementation, if the memory 301, the processor 302, and the communication interface 303 are integrated on a chip, the memory 301, the processor 302, and the communication interface 303 can communicate with each other through an internal interface.

[0108] The processor 302 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0109] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for determining the driving head movement trajectory as described above is implemented.

[0110] In the description of this specification, the descriptions referring to terms such as "an embodiment", "some embodiments", "example", "specific example", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0111] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0112] Any process or method description in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more N executable instructions for implementing a customized logic function or process. And the scope of the preferred embodiments of the present application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in the reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art of the embodiments of the present application.

[0113] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following well-known technologies in the art or their combination can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays, field programmable gate arrays, etc.

[0114] Those of ordinary skill in the art can understand that all or part of the steps carried out in implementing the above-described embodiment methods can be completed by instructing relevant hardware through a program, and the said program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0115] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for determining the movement trajectory of a driver's head, characterized in that, It includes the following steps: Determine whether the vehicle has collided; In the case where the vehicle has collided, obtain the current seat backrest angle, the current collision form and the current collision speed of the vehicle; Input the current seat backrest angle, the current collision form and the current collision speed into a preset head trajectory prediction model to obtain the head movement trajectory of the driver, wherein the preset head trajectory prediction model is constructed by matrix processing results of multiple collision parameters for a preset neural network.

2. The method according to claim 1, wherein Before inputting the angle of the vehicle seat, the current collision form and the current collision speed into the preset head trajectory prediction model to obtain the head position of the driver, it includes: Determine multiple collision parameters, wherein the multiple collision parameters include multiple seat backrest angles, multiple collision forms and multiple collision speeds; Respectively perform matrix processing on the multiple seat backrest angles, the multiple collision forms and the multiple collision speeds, and obtain a head movement trajectory matrix according to the matrix processing results; Establish the preset head trajectory prediction model according to the matrix processing results and the head movement trajectory matrix.

3. The method according to claim 2, characterized in that, The step of respectively performing matrix processing on the multiple seat backrest angles, the multiple collision forms and the multiple collision speeds, and obtaining a head movement trajectory matrix according to the matrix processing results includes: Perform matrix processing on the multiple seat backrest angles, the multiple collision forms and the multiple collision speeds to obtain a seat backrest angle matrix, a collision form matrix and a collision speed matrix; Determine multiple test combinations according to the seat backrest angle matrix, the collision form matrix and the collision speed matrix, and perform simulation on each test combination to obtain the head movement trajectory matrix.

4. The method according to claim 3, wherein The step of establishing the preset head trajectory prediction model according to the matrix processing results and the head movement trajectory matrix includes: Establish an initial matrix combination relationship according to the seat backrest angle matrix, the collision form matrix, the collision speed matrix and the head movement trajectory matrix; Perform unitization processing on the initial matrix combination relationship to obtain a unitized matrix combination relationship, and sample the processed matrix combination relationship to obtain the corresponding relationship between the unit condition matrix and the unit result matrix; Based on the corresponding relationship between the unit condition matrix and the unit result matrix, construct the preset neural network to obtain the preset head trajectory prediction model.

5. The method according to claim 1, wherein After obtaining the head movement trajectory of the driver, it includes: Determine the concentration area of the head movement trajectory of the driver, and determine the deployment parameters of the airbag according to the concentration area.

6. The method according to any one of claims 1-5, characterized in that, The collision form includes at least one of full-width frontal rigid collision, frontal offset rigid collision, frontal deformable barrier collision, and oblique frontal collision.

7. A device for determining a driver's head movement trajectory, characterized in that, It includes: A judgment module for judging whether the vehicle has collided; An acquisition module for obtaining the current seat backrest angle, the current collision form and the current collision speed of the vehicle in the case where the vehicle has collided; A generation module, configured to input the current seat backrest angle, the current collision form, and the current collision speed into a preset head trajectory prediction model to obtain the head movement trajectory of the driver, where the preset head trajectory prediction model is constructed by a preset neural network based on the matrix processing results of multiple collision parameters.

8. The device according to claim 7, characterized in that, Before inputting the angle of the vehicle seat, the current collision form, and the current collision speed into a preset head trajectory prediction model to obtain the head position of the driver, the generation module includes: A first determination unit, configured to determine multiple collision parameters, where the multiple collision parameters include multiple seat backrest angles, multiple collision forms, and multiple collision speeds; A processing unit, configured to perform matrix processing on the multiple seat backrest angles, the multiple collision forms, and the multiple collision speeds respectively, and obtain a head movement trajectory matrix according to the matrix processing results; An establishment unit, configured to establish the preset head trajectory prediction model according to the matrix processing results and the head movement trajectory matrix.

9. A vehicle, characterized in that, including: A memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the method for determining the head movement trajectory of the driver according to any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used for implementing the method for determining the head movement trajectory of the driver according to any one of claims 1-6.

Images