Self-adaptive control method, device and system of active safety belt, medium and vehicle

By obtaining information inside and outside the vehicle to calculate the target force, the adaptive control of the active seat belt is solved, and the problem of the inability to adjust the force in the existing technology is solved, the safety is improved, and it is suitable for more people.

CN118977670APending Publication Date: 2024-11-19GUANGZHOU AUTOMOBILE GROUP CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202410919891.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-09
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing active seat belts cannot adaptively adjust the force curve, resulting in low safety when used in different groups of people, especially possible unnecessary harm to vulnerable groups.

Method used

By obtaining the body status information of the personnel in the vehicle, the environmental information outside the vehicle and the vehicle status information, calculating the target force and duration, converting it into motor driving parameters, the adaptive control of the active seat belt is realized.

Benefits of technology

It improves the adaptability of active seat belts to different groups of people, enhances the safety of the whole vehicle, and ensures that the force of the seat belt can be adjusted more accurately under different circumstances, and is suitable for more people.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118977670A_ABST
    Figure CN118977670A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of automobile safety, in particular to a self-adaptive control method, device and system for an active safety belt, a medium and a vehicle. In the application, the target acting force of the active safety belt at the current moment and the duration of the target acting force are calculated according to the posture difference information, the information of the environment outside the vehicle and the state information of the vehicle, and the external environment of the vehicle and the state information of the vehicle serve as the basis for adjusting the acting force of the active safety belt; multi-aspect information influencing the active safety belt acting force is considered, the precision of calculating the active safety belt acting force and the duration time is improved, the target acting force and the duration time are converted into the driving parameters of the motor, the original driving parameters of the motor are covered, and the active safety belt is adaptively adjusted based on the driving parameters and the driving state. And the adjusted active safety belt can be suitable for more people, so that the safety of the whole vehicle is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of automobile safety technology, and in particular to an adaptive control method, device, system, medium and vehicle for an active safety belt. Background Art

[0002] With the rapid development of the automobile industry, the field of automobile safety has gradually moved from the traditional passive safety field to the active safety field. The active seat belt driven by the motor can actively intervene according to the vehicle driving information. Compared with the traditional mechanical active seat belt, it can respond to different road conditions earlier and protect the occupants. At the same time, it can also adjust the force curve of its motor according to the vehicle body information and feedback to the driver, so that the driver can make safe driving decisions.

[0003] At present, the active seat belt force curve is written into the control unit after calibration before the vehicle leaves the factory, and cannot be adaptively adjusted. In addition, due to the structure of the active seat belt itself, it is impossible to actively relax after tightening, and generally it is necessary to rely on the body's own elasticity to relax the active seat belt. Most active seat belt products will have multiple levels of force curves for selection to suit different groups of people, but there is a lot of room for improvement in terms of product convenience, safety and stability. If vulnerable groups such as the elderly, pregnant women and the disabled adjust the force incorrectly, it is easy to cause unnecessary harm.

[0004] Therefore, when adjusting the force curve of the active seat belt, how to improve the adaptability to different groups of people becomes an urgent problem to be solved. Summary of the invention

[0005] Based on this, it is necessary to provide an adaptive control method, device, system, medium and vehicle for an active seat belt in response to the above technical problems, so as to solve the problem of low safety caused by the inability to adaptively adjust the force curve of the active seat belt.

[0006] A first aspect of an embodiment of the present application provides an adaptive control method for an active seat belt, the adaptive control method comprising:

[0007] Acquire body posture information of a person in the vehicle at the current moment, environmental information outside the vehicle, and state information of the vehicle, and determine body posture difference information between the body posture information of the person and preset standard body posture information;

[0008] Calculating the target force of the active safety belt and the duration of the target force at the current moment according to the body posture difference information, the environment information outside the vehicle, the state information of the vehicle and a preset first force curve parameter prediction model;

[0009] The target force and the duration are converted into driving parameters of a motor, and the active seat belt is adaptively controlled according to the driving parameters and the driving state of the motor.

[0010] A second aspect of an embodiment of the present application provides an adaptive control device for an active seat belt, the adaptive control device comprising:

[0011] An acquisition module, used to acquire the body posture information of the person in the vehicle at the current moment, the environment information outside the vehicle and the state information of the vehicle, and determine the body posture difference information between the body posture information of the person and the preset standard body posture information;

[0012] a calculation module, configured to calculate a target force of the active safety belt and a duration of the target force at a current moment according to the body posture difference information, the environment information outside the vehicle, the state information and a preset first force curve parameter prediction model;

[0013] The control module is used to convert the target force and the duration into driving parameters of the motor, and to perform adaptive control on the active seat belt according to the driving parameters and the driving state of the motor.

[0014] A third aspect of an embodiment of the present application provides an active seat belt system, comprising: an active buckle and a controller, wherein the controller is used to control the adaptive adjustment of the active buckle and the active seat belt using the adaptive control method described in the first aspect.

[0015] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the adaptive control method as described in the first aspect above is implemented.

[0016] A fifth aspect of an embodiment of the present application provides a vehicle, comprising the above-mentioned active seat belt system.

[0017] Compared with the prior art, the present invention has the following beneficial effects:

[0018] The body information of the person in the vehicle at the current moment, the environmental information outside the vehicle and the state information of the vehicle are obtained, the body difference information between the body information of the person and the preset standard body information is determined, and the target force and the duration of the target force of the active safety belt at the current moment are calculated according to the body difference information, the environmental information outside the vehicle, the state information of the vehicle and the preset first force curve parameter prediction model, and the target force and the duration are converted into the driving parameters of the motor, and the active safety belt is adaptively controlled according to the driving parameters and the driving state of the motor. In the present application, the target force and the duration of the target force of the active safety belt at the current moment are calculated according to the body difference information, the environmental information outside the vehicle and the state information of the vehicle, the external environment of the vehicle and the state information of the vehicle are used as the basis for adjusting the force of the active safety belt, and various information affecting the force of the active safety belt is taken into account, so as to improve the accuracy of calculating the force and duration of the active safety belt, convert the target force and the duration into the driving parameters of the motor, cover the original driving parameters of the motor, and adaptively adjust the active safety belt based on the driving parameters and the driving state, so that the adjusted active safety belt can be applied to more people, thereby improving the safety of the whole vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0020] Figure 1 is a flow chart of an adaptive control method for an active seat belt provided in Embodiment 1 of the present invention;

[0021] Figure 2 It is a schematic diagram of the actuation of an active seat belt and an active seat belt buckle when a motor driving state is in a tensioned state provided by the second embodiment of the present invention;

[0022] Figure 3 It is a schematic diagram of the actuation of an active seat belt and an active seat belt buckle when a motor driving state is in a relaxed state provided by Embodiment 3 of the present invention;

[0023] Figure 4 1 is a flow chart of an adaptive control method for an active seat belt provided in a fourth embodiment of the present invention;

[0024] Figure 5 is a structural block diagram of an adaptive control device for an active seat belt provided in a fifth embodiment of the present invention;

[0025] Figure 6An active seat belt system provided by Embodiment 6 of the present invention;

[0026] Figure 7 It is a schematic diagram of a vehicle provided in Embodiment 7 of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0029] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0030] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.

[0031] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" etc. described in the specification of the present invention mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0034] In order to illustrate the technical solution of the present invention, the following is described through specific embodiments.

[0035] See also Figure 1 , is a flow chart of an adaptive control method for an active seat belt provided in the first embodiment of the present invention, such as Figure 1 As shown, the adaptive control method of the active seat belt may include the following steps:

[0036] S101: Obtaining the body posture information of the person in the vehicle at the current moment, the environment information outside the vehicle and the state information of the vehicle, and determining the body posture difference information between the person's body posture information and the preset standard body posture information.

[0037] In step S101, the body information is information describing the human body state of the person in the vehicle, and the body information may include the age information, gender information, height information, weight information, sitting posture information, etc. of the person in the vehicle, the environment information outside the vehicle is information describing the environment in which the vehicle is located, and may include climate information, road condition information, road traffic information, etc., and the vehicle state information is information describing the state of the vehicle itself, and may include vehicle chassis information and body information, etc. According to the body information of the person in the vehicle at the current moment and the preset standard body information, the body difference information between the body information of the person and the preset standard body information is determined.

[0038] In this embodiment, when obtaining the body information of the people in the vehicle at the current moment, the body images of the people in the vehicle are collected, and a three-dimensional model of the people in the vehicle is constructed based on the body images. Based on the occupant image data and the three-dimensional model, the body feature information of the portrait, such as age information, gender information, height information, weight information and sitting posture information, is obtained.

[0039] It should be noted that when collecting body images of people in the vehicle, it can be collected through the camera equipment in the vehicle, such as the 3D ToF (Time of Flight) camera in the vehicle, etc., and the body images of people in the vehicle can be collected using the 3D ToF camera. Based on the body images, a three-dimensional model of the corresponding person is constructed to facilitate determining the body information of the person based on the three-dimensional model.

[0040] When constructing a three-dimensional model of the corresponding person based on a human body image, the human body image is input into a preset key point detection algorithm to obtain multiple detection key points in the human body image and the target detection coordinates of each detection key point. Based on the multiple target detection coordinates and the target human body model corresponding to the human body image in the preset human body construction model, a human body vector corresponding to the human body image and a target human body three-dimensional model corresponding to the human body vector are generated.

[0041] It should be noted that before fitting according to multiple target detection coordinates and the preset coordinates corresponding to each detection key point in the preset human body construction model, the gender detection model is used to predict the gender of the human body in the human image to obtain the predicted gender and the predicted probability of the predicted gender. If the gender probability is greater than or equal to the preset threshold, the basic human body model corresponding to the predicted gender is determined as the target human body three-dimensional model.

[0042] According to the corresponding human body image and the target human body three-dimensional model, the age information, gender information, height information, weight information and sitting posture information of the occupant of the vehicle are determined.

[0043] Obtain preset standard body information, wherein the preset standard body information includes age information, gender information, height information, weight information, and sitting posture information in the standard human 3D model. According to the age information, gender information, height information, weight information, and sitting posture information of the occupant, and the age information, gender information, height information, weight information, and sitting posture information in the standard human 3D model, calculate the body difference information corresponding to the occupant and the standard human 3D model.

[0044] When obtaining environmental information outside the vehicle, it can be identified and obtained through sensors such as cameras outside the vehicle. The camera outside the vehicle takes pictures of the surroundings of the vehicle and transmits the captured images to the image processing module in the vehicle. The module processes the images and transmits the image data to the background. The background identifies the environmental information and obtains the recognition results, wherein the recognition results include climate information at the current moment, so as to facilitate tightening the active seat belts to indicate safe driving in severe weather conditions; the recognition results also include road condition information, so as to facilitate tightening the active seat belts to indicate safe driving in severe road conditions, such as gravel or obviously damaged roads; the recognition results also include road traffic information, so as to facilitate tightening the active seat belts to indicate safe driving in dangerous traffic conditions, such as trucks in front and behind the current road or traffic accidents ahead.

[0045] When obtaining the vehicle status information, it can be detected and identified through the vehicle sensor. For example, the vehicle sensor can detect the vehicle chassis information, such as the vehicle's current speed information, acceleration and brake pedal information, and steering information; the vehicle sensor can also detect the vehicle body information, such as the vehicle's body suspension information and body tilt angle information, and identify the overall state of the vehicle based on the vehicle chassis information and body information, such as whether the vehicle is in a dangerous state such as dangerous driving, out of control, or on the edge of a rollover. If it is identified that the overall state of the vehicle is in a dangerous state such as dangerous driving, out of control, or on the edge of a rollover, the active seat belt tensioning force is adjusted to avoid safety accidents.

[0046] S102: Calculate the target force and duration of the target force of the active seat belt at the current moment according to the body posture difference information, the environment information outside the vehicle, the state information of the vehicle and a preset first force curve parameter prediction model.

[0047] In step S102, the target force and the duration of the target force of the active safety belt at the current moment are calculated according to the posture difference information, the environment information outside the vehicle, the state information of the vehicle and the preset first force curve parameter prediction model, wherein the preset first force curve parameter prediction model is used to predict the parameters in the first force curve, including the target force of the active safety belt and the duration of the target force. The first force curve parameter prediction model corresponds to different parameter prediction models in different actuation modes, and each actuation mode corresponds to a first force curve parameter prediction model. When the actuation mode changes, the corresponding first force curve parameter prediction model also changes accordingly. The first force curve parameter prediction model is used to represent the corresponding relationship between the posture difference information, the environment information outside the vehicle, the state information of the vehicle and the parameters in the force curve. Among them, the target force of the active safety belt is the force acting on the active safety belt at the current moment, that is, the tension of the active safety belt. If the target force of the active safety belt is larger, the tension of the active safety belt is larger, and it is more conducive to fixing the person. The duration of the target force is the time that the target force needs to last at the current moment.

[0048] In this embodiment, a preset first force curve parameter prediction model is obtained, wherein the first force curve parameter prediction model can be a deep learning model, which is used to predict the parameters in the first force curve, that is, the body difference information, the environment information outside the vehicle and the state information of the vehicle are input into the first force curve parameter prediction model, and the target force of the active safety belt and the duration of the target force are output. The target force of the active safety belt is the force acting on the active safety belt at the current moment, that is, the tension of the active safety belt. If the target force of the active safety belt is larger, the tension of the active safety belt is larger, and it is more conducive to fixing the person. The duration of the target force is the time that the target force needs to last at the current moment.

[0049] It should be noted that the first force curve parameter prediction model corresponds to different parameter prediction models under different actuation modes, and each actuation mode corresponds to a first force curve parameter prediction model. When the actuation mode changes, the corresponding first force curve parameter prediction model also changes accordingly. For example, when the actuation mode is the normal seat height mode, it corresponds to a first force curve parameter prediction model, and when the actuation mode is the seat lower than normal height mode, it corresponds to another first force curve parameter prediction model. If the actuation mode changes from the normal seat height mode to the seat lower than normal height mode, then when calculating the target force and duration, the first force curve parameter prediction model corresponding to the normal seat height mode is changed to the first force curve parameter prediction model corresponding to the seat lower than normal height mode. The corresponding first force curve parameter prediction model is obtained according to the corresponding actuation mode.

[0050] It should be noted that the prediction logic of the first force curve parameter prediction model is that the greater the posture difference information, the greater the predicted target force, and the longer the duration of the target force; if the environmental information outside the vehicle is worse, the predicted target force is greater, and the duration of the target force is longer; if the vehicle status information is more dangerous, the predicted target force is greater, and the duration of the target force is longer.

[0051] It should be noted that the target force at the current moment increases or decreases based on the target force at the previous moment. When the target force at the current moment increases relative to the target force at the previous moment, it is considered that the direction of the target force at the current moment is the same as the direction of the target force at the previous moment. When the target force at the current moment decreases relative to the target force at the previous moment, it is considered that the direction of the target force at the current moment is opposite to the direction of the target force at the previous moment.

[0052] S103: Convert the target force and duration into driving parameters of the motor, and perform adaptive control on the active seat belt according to the driving parameters and the driving state of the motor.

[0053] In step S103, the driving parameters of the motor include the speed and torque of the motor, which are used to drive the corresponding motor to operate, and the active seat belt is adaptively controlled so that the motor applies the target force to the active seat belt, wherein the adaptive control may include the tensioning control and the loosening control of the active seat belt.

[0054] In this embodiment, the target force and duration are converted into driving parameters of the motor. During the conversion, the conversion method in the prior art can be used for conversion, which is not limited in this embodiment.

[0055] At this moment, the active seat belt is adaptively controlled according to the driving parameters and the driving state of the motor. The driving state of the motor includes a tightening state and a loosening state. Different driving states have different driving directions of the motor. After the driving parameters and the driving state of the motor are determined, the motor runs according to the corresponding driving parameters and the driving state of the motor to tighten or loosen the active seat belt.

[0056] It should be noted that when the vehicle is driving, the original force curve of the vehicle is obtained. When the corresponding target force and duration are not predicted, the motor outputs the corresponding force and duration in the original force curve. The original force curve is determined according to the corresponding actuation mode, and different actuation modes correspond to different original force curves. The horizontal axis in the original force curve is time, and the vertical axis is the corresponding force.

[0057] It should be noted that the motor directly acts on the active seat belt, and the active seat belt is adaptively adjusted according to the predicted target force and duration.

[0058] Optionally, before the active seat belt is adaptively controlled according to the driving parameters and the driving state of the motor, the method further includes:

[0059] Get the target force at the previous moment;

[0060] According to the target force of the active seat belt at the current moment and the target force of the active seat belt at the previous moment, determining whether the direction of the target force of the active seat belt at the current moment is the same as the direction of the target force of the active seat belt at the previous moment;

[0061] If the directions are the same, it is determined that the driving state of the motor is in the tensioned state;

[0062] If the directions are different, it is determined that the driving state of the motor is a relaxed state.

[0063] In this embodiment, before the active safety belt is adaptively controlled according to the driving parameters and the driving state of the motor, the driving state of the motor is determined to obtain the target force at the previous moment. According to the target force of the active safety belt at the current moment and the target force of the active safety belt at the previous moment, it is determined whether the direction of the target force of the active safety belt at the current moment is the same as that of the target force of the active safety belt at the previous moment, wherein the target force at the current moment is increased or decreased based on the target force at the previous moment, when the target force at the current moment increases relative to the target force at the previous moment, it is considered that the direction of the target force at the current moment is the same as that of the target force at the previous moment, and when the target force at the current moment decreases relative to the target force at the previous moment, it is considered that the direction of the target force at the current moment is opposite to that of the target force at the previous moment, that is, the direction of the target force at the current moment is different from that of the target force at the previous moment.

[0064] If the directions are the same, the driving state of the motor is determined to be a tightened state, and if the directions are different, the driving state of the motor is determined to be a relaxed state. The tightened state means that the active seat belt is tightened based on the previous moment, and the relaxed state means that the active seat belt is relaxed based on the previous moment.

[0065] Optionally, the active seat belt is adaptively controlled according to the driving parameters and the driving state of the motor, including:

[0066] If the driving state of the motor is the tensioning state, the motor is controlled to tighten the active seat belt according to the driving parameters, and the motor is controlled to tighten the active seat belt buckle connected to the active seat belt;

[0067] If the driving state of the motor is a released state, the motor is controlled to release the active seat belt buckle according to the driving parameters.

[0068] In this embodiment, when the active seat belt is adaptively controlled, the active seat belt needs to be processed differently according to the driving states of different motors. If the driving state of the motor is the tensioning state, the motor is controlled to tension the active seat belt according to the driving parameters, and the motor is controlled to tighten the active seat belt buckle connected to the active seat belt, that is, the target force is applied to the active seat belt, and when it is tightened, the active seat belt buckle connected to the active seat belt is also tightened.

[0069] See also Figure 2, is a schematic diagram of an actuation of an active seat belt and an active seat belt buckle when the driving state of a motor is in a tensioned state provided by a second embodiment of the present invention. When the driving state of the motor is in a tensioned state, the controller controls the motor to provide a downward pulling force to the active seat belt and the active seat belt buckle, so that the active seat belt and the active seat belt buckle are tightened, wherein the motor provides a downward pulling force to the active seat belt and the active seat belt buckle through a pull wire, and the pull wire can be a copper wire or other metal wire, Figure 2 The pull wire is a copper wire, which connects the motor and the active seat belt buckle through a pulley. Figure 2 The retractor in the seat belt is used to tighten the cable, so that the active seat belt buckle moves in the direction of the cable tightening, thereby fixing the active seat belt buckle.

[0070] If the driving state of the motor is a relaxed state, the motor is controlled to relax the active seat belt according to the driving parameters, and the motor is controlled to relax the active seat belt buckle, that is, the target force is applied to the active seat belt, and when it is relaxed, the active seat belt buckle connected to the active seat belt is relaxed, that is, the purpose of relaxation is achieved by moving the active seat belt buckle.

[0071] See also Figure 3 , is a schematic diagram of an actuation of an active seat belt and an active seat belt buckle when the driving state of a motor is in a relaxed state provided by a third embodiment of the present invention. When the driving state of the motor is in a relaxed state, the controller controls the motor to provide an upward pulling force to the active seat belt buckle to relax the active seat belt buckle, wherein the motor provides an upward pulling force to the active seat belt buckle through a pull wire, and the pull wire may be a copper wire or other metal wire, Figure 3 The pull wire is a copper wire, which connects the motor and the main active seat belt buckle through a pulley. Figure 3 The retractor in the seat belt is used to relax the cable, release a longer cable, and move the active seat belt buckle in the direction of the cable relaxation.

[0072] The body information of the person in the vehicle at the current moment, the environmental information outside the vehicle and the state information of the vehicle are obtained, the body difference information between the body information of the person and the preset standard body information is determined, and the target force and the duration of the target force of the active safety belt at the current moment are calculated according to the body difference information, the environmental information outside the vehicle, the state information of the vehicle and the preset first force curve parameter prediction model, and the target force and the duration are converted into the driving parameters of the motor, and the active safety belt is adaptively controlled according to the driving parameters and the driving state of the motor. In the present application, the target force and the duration of the target force of the active safety belt at the current moment are calculated according to the body difference information, the environmental information outside the vehicle and the state information of the vehicle, and the external environment and the state information of the vehicle are used as the basis for adjusting the active safety belt force, and the various factors affecting the active safety belt force are taken into account, so as to improve the accuracy of calculating the active safety belt force and duration, convert the target force and duration into the driving parameters of the motor, cover the original driving parameters of the motor, and adaptively adjust the active safety belt based on the driving parameters and the driving state, so that the adjusted active safety belt can be applied to more people, thereby improving the safety of the whole vehicle.

[0073] See also Figure 4 , is a flow chart of an adaptive control method for an active seat belt provided by a fourth embodiment of the present invention, such as Figure 4 As shown, the adaptive control method of the active seat belt may further include the following steps.

[0074] S401: when the vehicle is stationary or restarted, obtaining body posture information of a person in the vehicle at the current moment, and determining body posture difference information between the body posture information of the person and preset standard body posture information;

[0075] S402: Calculating the target force and duration of the target force of the active safety belt at the current moment according to the body posture difference information and a preset second force curve parameter prediction model;

[0076] S403: Convert the target force and duration into driving parameters of the motor, and perform adaptive control on the active seat belt according to the driving parameters and the driving state of the motor.

[0077] In this embodiment, when the vehicle is stationary or restarted, the target force and duration of the target force of the active safety belt at the current moment can be calculated based on the posture difference information. Therefore, when the vehicle is stationary or restarted, the posture information of the person in the vehicle at the current moment is obtained, and the posture difference information between the person's posture information and the preset standard posture information is determined.

[0078] In this embodiment, the body information is information describing the human body state of the occupant, and the body information may include the age information, gender information, height information, weight information, sitting posture information, etc. of the occupant. When obtaining the body information of the occupant in the vehicle at the current moment, the body image of the occupant in the vehicle is collected, and a three-dimensional model of the occupant in the vehicle is constructed based on the body image. Based on the occupant image data and the three-dimensional model, the body feature information of the portrait, such as the age information, gender information, height information, weight information, sitting posture information, etc., is obtained.

[0079] It should be noted that when collecting body images of people in the vehicle, it can be collected through the camera equipment in the vehicle, such as the 3D ToF (Time of Flight) camera in the vehicle, etc., and the body images of people in the vehicle can be collected using the 3D ToF camera. Based on the body images, a three-dimensional model of the corresponding person is constructed to facilitate determining the body information of the person based on the three-dimensional model.

[0080] When constructing a three-dimensional model of the corresponding person based on a human body image, the human body image is input into a preset key point detection algorithm to obtain multiple detection key points in the human body image and the target detection coordinates of each detection key point. Based on the multiple target detection coordinates and the target human body model corresponding to the human body image in the preset human body construction model, a human body vector corresponding to the human body image and a target human body three-dimensional model corresponding to the human body vector are generated.

[0081] It should be noted that before fitting according to multiple target detection coordinates and the preset coordinates corresponding to each detection key point in the preset human body construction model, the gender detection model is used to predict the gender of the human body in the human image to obtain the predicted gender and the predicted probability of the predicted gender. If the gender probability is greater than or equal to the preset threshold, the basic human body model corresponding to the predicted gender is determined as the target human body three-dimensional model.

[0082] According to the corresponding human body image and the target human body three-dimensional model, the age information, gender information, height information, weight information and sitting posture information of the occupant of the vehicle are determined.

[0083] In this embodiment, the target force of the active safety belt at the current moment and the duration of the target force are calculated according to the posture difference information and the preset second force curve parameter prediction model, wherein the preset second force curve parameter prediction model is used to predict the parameters in the second force curve, including the target force of the active safety belt and the duration of the target force. The second force curve parameter prediction model corresponds to different parameter prediction models in different actuation modes, and each actuation mode corresponds to a second force curve parameter prediction model. When the actuation mode changes, the corresponding second force curve parameter prediction model also changes accordingly. The second force curve parameter prediction model is used to represent the corresponding relationship between the posture difference information and the parameters in the force curve. Among them, the target force of the active safety belt is the force acting on the active safety belt at the current moment, that is, the tension of the active safety belt. If the target force of the active safety belt is larger, the tension of the active safety belt is larger, so as to fix the person, and the duration of the target force is the time that the target force needs to last at the current moment.

[0084] For example, when the actuation mode is the normal seat height mode, a second force curve parameter prediction model corresponds to it, and when the actuation mode is the seat lower than normal height mode, another second force curve parameter prediction model corresponds to it. If the actuation mode changes from the normal seat height mode to the seat lower than normal height mode, when calculating the target force and duration, the second force curve parameter prediction model corresponding to the normal seat height mode is changed to the second force curve parameter prediction model corresponding to the seat lower than normal height mode. The corresponding second force curve parameter prediction model is obtained according to the corresponding actuation mode.

[0085] In this embodiment, a preset second force curve parameter prediction model is obtained, wherein the second force curve parameter prediction model can be a deep learning model, which is used to predict the parameters in the second force curve, that is, the posture difference information is input into the second force curve parameter prediction model, and the target force of the active safety belt and the duration of the target force are output. The target force of the active safety belt is the force acting on the active safety belt at the current moment, that is, the tension of the active safety belt. If the target force of the active safety belt is greater, the degree of tension of the active safety belt is greater, so as to fix the person, and the duration of the target force is the time that the target force needs to last at the current moment.

[0086] It should be noted that the prediction logic of the second force curve parameter prediction model is that the greater the body posture difference information is, the greater the predicted target force is and the longer the duration of the target force is.

[0087] It should be noted that the target force at the current moment increases or decreases based on the target force at the previous moment. When the target force at the current moment increases relative to the target force at the previous moment, it is considered that the direction of the target force at the current moment is the same as the direction of the target force at the previous moment. When the target force at the current moment decreases relative to the target force at the previous moment, it is considered that the direction of the target force at the current moment is opposite to the direction of the target force at the previous moment.

[0088] In this embodiment, the target force and duration are converted into driving parameters of the motor. During the conversion, the conversion method in the prior art can be used for conversion, which is not limited in this embodiment.

[0089] At the current moment, the active seat belt is adaptively controlled according to the driving parameters and the driving state of the motor, wherein the adaptive control may include the tensioning control and the loosening control of the active seat belt. The driving state of the motor includes the tensioning state and the loosening state. The driving direction of the motor is different in different driving states. After the driving parameters and the driving state of the motor are determined, the motor operates according to the corresponding driving parameters and the driving state of the motor to tighten or loosen the active seat belt.

[0090] It should be noted that when the vehicle is driving, the original force curve of the vehicle is obtained. When the corresponding target force and duration are not predicted, the motor outputs the corresponding force and duration in the original force curve. The original force curve is determined according to the corresponding actuation mode, and different actuation modes correspond to different original force curves. The horizontal axis in the original force curve is time, and the vertical axis is the corresponding force.

[0091] Optionally, the active seat belt is adaptively controlled according to the driving parameters and the driving state of the motor, including:

[0092] If the driving state of the motor is the tensioning state, the motor is controlled to tighten the active seat belt according to the driving parameters, and the motor is controlled to tighten the active seat belt buckle connected to the active seat belt;

[0093] If the driving state of the motor is a released state, the motor is controlled to release the active seat belt buckle according to the driving parameters.

[0094] In this embodiment, when the active safety belt is adaptively controlled, the driving states of different motors require different processing of the active safety belt. If the driving state of the motor is a tensioning state, the motor is controlled to tighten the active safety belt according to the driving parameters, and the motor is controlled to tighten the active safety belt buckle connected to the active safety belt, that is, the target force is applied to the active safety belt, and when it is tightened, the active safety belt buckle connected to the active safety belt is also tightened, that is, the active safety belt buckle is fixed to a position where it cannot move.

[0095] See also Figure 2 , is a schematic diagram of an actuation of an active seat belt and an active seat belt buckle when the driving state of a motor is in a tensioned state provided by a second embodiment of the present invention. When the driving state of the motor is in a tensioned state, the controller controls the motor to provide a downward pulling force to the active seat belt and the active seat belt buckle, so that the active seat belt and the active seat belt buckle are tightened, wherein the motor provides a downward pulling force to the active seat belt and the active seat belt buckle through a pull wire, and the pull wire can be a copper wire or other metal wire, Figure 2 The pull wire is a copper wire, which connects the motor and the active seat belt buckle through a pulley. Figure 2 The retractor in the seat belt is used to tighten and contract the cable, so that the active seat belt buckle moves in the direction of the cable tightening, thereby fixing the active seat belt buckle.

[0096] If the driving state of the motor is a relaxed state, the motor is controlled to relax the active seat belt according to the driving parameters, and the motor is controlled to relax the active seat belt buckle, that is, the target force is applied to the active seat belt, and when it is relaxed, the active seat belt buckle connected to the active seat belt is relaxed, that is, the purpose of relaxation is achieved by moving the active seat belt buckle.

[0097] See also Figure 3 , is a schematic diagram of an actuation of an active seat belt and an active seat belt buckle when the driving state of a motor is in a relaxed state provided by a third embodiment of the present invention. When the driving state of the motor is in a relaxed state, the controller controls the motor to provide an upward pulling force to the active seat belt buckle to relax the active seat belt buckle, wherein the motor provides an upward pulling force to the active seat belt buckle through a pull wire, and the pull wire may be a copper wire or other metal wire, Figure 3 The pull wire is a copper wire, which connects the motor and the active seat belt buckle through a pulley. Figure 3 The retractor in the seat belt is used to relax the cable, release a longer cable, and move the active seat belt buckle in the direction of the cable relaxation.

[0098] See also Figure 5 , is a structural block diagram of an adaptive control device for an active seat belt provided by Embodiment 5 of the present invention. For the sake of convenience, only the part related to the embodiment of the present invention is shown. Figure 5The adaptive control device 50 includes: an acquisition module 51, a calculation module 52, and a control module 53.

[0099] The acquisition module 51 is used to acquire the body posture information of the person in the vehicle at the current moment, the environment information outside the vehicle and the state information of the vehicle, and determine the body posture difference information between the body posture information of the person and the preset standard body posture information.

[0100] The calculation module 52 is used to calculate the target force and duration of the target force of the active safety belt at the current moment according to the body posture difference information, the environment information outside the vehicle, the state information of the vehicle and the preset first force curve parameter prediction model.

[0101] The control module 53 is used to convert the target force and duration into driving parameters of the motor, and perform adaptive control on the active seat belt according to the driving parameters and the driving state of the motor.

[0102] Optionally, the adaptive control device 50 further includes:

[0103] The second acquisition module is used to obtain the target force at the previous moment;

[0104] The judging module is used to judge whether the direction of the target force of the active seat belt at the current moment is the same as the direction of the target force of the active seat belt at the previous moment according to the target force of the active seat belt at the current moment and the target force of the active seat belt at the previous moment.

[0105] The first determination module is used to determine that the driving state of the motor is a tensioned state if the directions are the same.

[0106] The second determination module is used to determine that the driving state of the motor is a relaxation state if the directions are different.

[0107] Optionally, the control module 53 includes:

[0108] The first control unit is used to control the motor to tighten the active seat belt according to the driving parameters if the driving state of the motor is the tensioning state, and control the motor to tighten the active seat belt buckle connected to the active seat belt.

[0109] The second control unit is used for controlling the motor to release the active seat belt buckle according to the driving parameters if the driving state of the motor is a release state.

[0110] Optionally, the adaptive control device 50 further includes:

[0111] The determination module is used to obtain the body posture information of the person in the vehicle at the current moment when the vehicle is stationary or restarted, and determine the body posture difference information between the person's body posture information and the preset standard body posture information.

[0112] The second calculation module is used to calculate the target force and the duration of the target force of the active safety belt at the current moment according to the body posture difference information and a preset second force curve parameter prediction model.

[0113] The second control module is used to convert the target force and duration into driving parameters of the motor, and perform adaptive control on the active seat belt according to the driving parameters and the driving state of the motor.

[0114] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0115] See also Figure 6 , Figure 6 An active seat belt system provided in Embodiment 6 of the present invention includes: an active buckle and a controller, wherein the controller is used to control the active buckle and the active seat belt to be adaptively adjusted using the above-mentioned adaptive control method. The active buckle includes an active seat belt buckle, a retractor and a motor, wherein the active seat belt buckle and the retractor are connected by a copper wire, wherein the copper wire between the active seat belt buckle and the retractor changes the direction of the force in the copper wire through a pulley, and the motor is connected to the retractor so that the motor drives the retractor to tighten or loosen the active seat belt buckle.

[0116] like Figure 6 (a), in the tensioning state, the controller controls the motor to drive the retractor to tighten the active seat belt buckle. The motor provides downward pulling force for the active seat belt buckle, and the retractor contracts the copper wire to move the active seat belt buckle in the direction of the tensioning wire, thereby fixing the active seat belt buckle. Figure 6 (b), in the relaxed state, the controller controls the motor to drive the retractor to relax the active seat belt buckle. The motor provides an upward pulling force to the active seat belt buckle, and the retractor releases the copper wire, causing the active seat belt buckle to move in the direction of the wire relaxation.

[0117] It should be noted that the controller for controlling the adaptive adjustment of the active buckle and the active safety belt can be one or two. When there is one controller, the same controller is used to control the adaptive adjustment of the active buckle and the active safety belt, including the tightening adjustment and the loosening adjustment. When there are two controllers, one of the controllers is used to control the tightening adjustment of the active buckle and the active safety belt, and the other controller is used to control the loosening adjustment of the active buckle and the active safety belt.

[0118] The present invention implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0119] The present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by a computer program product. When the computer program product runs on a computer device, the computer device can implement the steps in the above-mentioned method embodiment when executing.

[0120] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0122] In the embodiments provided by the present invention, it should be understood that the disclosed devices / computer equipment and methods can be implemented in other ways. For example, the device / computer equipment embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

[0125] See also Figure 7 , Figure 7 is a schematic diagram of a vehicle 70 provided in Embodiment 8 of the present invention, wherein the vehicle includes the above-mentioned active seat belt system.

Claims

1. An adaptive control method for an active seat belt, characterized in that: The adaptive control method comprises: Acquire body posture information of a person in the vehicle at the current moment, environmental information outside the vehicle, and state information of the vehicle, and determine body posture difference information between the body posture information of the person and preset standard body posture information; Calculating the target force of the active safety belt and the duration of the target force at the current moment according to the body posture difference information, the environment information outside the vehicle, the state information of the vehicle and a preset first force curve parameter prediction model; The target force and the duration are converted into driving parameters of a motor, and the active seat belt is adaptively controlled according to the driving parameters and the driving state of the motor.

2. The adaptive control method according to claim 1, characterized in that: Before the active safety belt is adaptively controlled according to the driving parameters and the driving state of the motor, the method further includes: Get the target force at the previous moment; According to the target force of the active safety belt at the current moment and the target force of the active safety belt at the previous moment, determining whether the direction of the target force of the active safety belt at the current moment is the same as the direction of the target force of the active safety belt at the previous moment; If the directions are the same, it is determined that the driving state of the motor is a tensioned state; If the directions are different, it is determined that the driving state of the motor is a relaxed state.

3. The adaptive control method according to claim 2, characterized in that: The method of adaptively controlling the active seat belt according to the driving parameters and the driving state of the motor includes: If the driving state of the motor is a tensioning state, then according to the driving parameters, the motor is controlled to tighten the active seat belt, and the motor is controlled to tighten the active seat belt buckle connected to the active seat belt; If the driving state of the motor is a release state, the motor is controlled to release the active seat belt buckle according to the driving parameter.

4. The adaptive control method according to claims 1 to 3, characterized in that: The adaptive control method further comprises: When the vehicle is stationary or restarted, obtaining body posture information of a person in the vehicle at the current moment, and determining body posture difference information between the body posture information of the person and preset standard body posture information; Calculating the target force of the active safety belt and the duration of the target force at the current moment according to the posture difference information and a preset second force curve parameter prediction model; The target force and the duration are converted into driving parameters of a motor, and the active seat belt is adaptively controlled according to the driving parameters and the driving state of the motor.

5. An adaptive control device for an active seat belt, characterized in that: The adaptive control device comprises: An acquisition module, used to acquire the body posture information of the person in the vehicle at the current moment, the environment information outside the vehicle and the state information of the vehicle, and determine the body posture difference information between the body posture information of the person and the preset standard body posture information; a calculation module, configured to calculate a target force of the active safety belt and a duration of the target force at a current moment according to the body posture difference information, the environment information outside the vehicle, the state information of the vehicle and a preset first force curve parameter prediction model; The control module is used to convert the target force and the duration into driving parameters of the motor, and to perform adaptive control on the active seat belt according to the driving parameters and the driving state of the motor.

6. The adaptive control device according to claim 5, characterized in that: The adaptive control device also includes: A determination module, used for obtaining body posture information of a person in the vehicle at a current moment when the vehicle is stationary or restarted, and determining body posture difference information between the body posture information of the person and preset standard body posture information; A second calculation module, configured to calculate the target force of the active safety belt and the duration of the target force at the current moment according to the posture difference information and a preset second force curve parameter prediction model; The second control module is used to convert the target force and the duration into driving parameters of the motor, and perform adaptive control on the active seat belt according to the driving parameters and the driving state of the motor.

7. An active seat belt system, characterized in that: include: An active buckle and a controller, wherein the controller is used to control the adaptive adjustment of the active buckle and the active safety belt using the adaptive control method of claims 1-4.

8. The active seat belt system according to claim 7, characterized in that: The active buckle comprises an active seat belt buckle, a retractor and a motor. The active seat belt buckle and the retractor are connected via a pulley, and the motor drives the retractor to tighten or loosen the active seat belt buckle.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the adaptive control method according to any one of claims 1 to 4 is implemented.

10. A vehicle, characterized in that: The vehicle includes the active seat belt system of claim 7.

Citation Information

Patent Citations

  • Safety belt lock catch adjusting method and device

    CN113436250A

  • System and method for enhancing safety of driver and passengers through automobile safety belt

    CN113511170A

  • Self-adaptive adjusting type safety belt system and adjusting method

    CN114954348A

  • procedure for controlling a seat belt pretensioner

    DE102016014807A1

  • Belt buckle for a safety belt device in a motor vehicle

    WO2013045027A1