Vehicle roll-over protection method, device, vehicle, medium and program

Abstract

The application relates to the technical field of vehicles, in particular to a vehicle rollover protection method and device, a vehicle, a medium and a program, wherein the method comprises the following steps: acquiring an angular velocity of a vehicle in a target direction and accelerations of the vehicle in multiple directions under a rollover condition; calculating a rollover end probability of the vehicle according to the angular velocity and the accelerations; and controlling the vehicle to perform a rollover protection action according to the rollover end probability. Therefore, the problems that, in the related art, the vehicle is unlocked at the same time as the airbag point explosion caused by the vehicle collision, the user is easily caused to suffer secondary injury in the collision, the vehicle safety is poor, the user experience is poor and the like are solved.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a vehicle rollover protection method, device, vehicle, medium, and procedure. Background Technology

[0002] With the increasing number of cars on the road, people are paying more and more attention to the safety performance of vehicles. Currently, the airbag electronic control unit has integrated a five-axis yaw angle sensor, which can detect whether the vehicle has rolled over, and when a rollover occurs, it will send a trigger signal to deploy the airbags, perform an emergency power cut, send an E-call rescue signal, and unlock the doors.

[0003] In related technologies, the door unlocking strategy in rollover situations is the same as in other collision situations such as frontal and side impacts: an unlocking signal is sent to unlock the door at the same time as the airbag deploys. However, in some high-speed rollover situations, due to the large angular velocity of the vehicle rollover, the vehicle will continue to roll at high speed for a period of time after the airbags deploy and the doors unlock. This duration varies depending on the initial rollover speed and the obstacles on site. Sending an unlocking signal to unlock the door at the same time as the airbags deploys can easily cause secondary injuries to the occupants, resulting in poor vehicle safety and a poor user experience. Summary of the Invention

[0004] This application provides a vehicle rollover protection method, device, vehicle, storage medium, and program product to solve the problem in the related art that when a vehicle collision occurs and the airbags deploy, unlocking the vehicle at the same time can easily cause secondary injuries to the user during the collision, resulting in poor vehicle safety and a poor user experience.

[0005] The first aspect of this application provides a vehicle rollover protection method, comprising the following steps: acquiring the angular velocity in a target direction and the acceleration in multiple directions of the vehicle during a rollover; calculating the rollover termination probability of the vehicle based on the angular velocity and the acceleration; and controlling the vehicle to perform a rollover protection action based on the rollover termination probability.

[0006] Optionally, the formula for calculating the roll-off end probability is:

[0007]

[0008] Where y is the probability that the roll has ended at the current moment, and χ = [ω x θ x θ x 2 +ω x 2 α y α z ], where ωx Let θ be the angular velocity of the vehicle around the x-axis. x For ω x From the perspective of obtaining the integral, α y Let α be the acceleration of the vehicle along the y-axis. z Let K be the vehicle's acceleration along the z-axis. K and b are model parameters for the current vehicle model. K = [K1, K2, K3, K4, K5].

[0009] Optionally, controlling the vehicle to perform rollover protection actions based on the rollover termination probability includes: if the rollover termination probability is greater than a preset probability, controlling at least one of the vehicle's doors to unlock, windows to open, sunroof to open, and trunk to open; if the rollover termination probability is less than or equal to the preset probability, controlling the vehicle's doors to lock, windows to close, sunroof to close, and trunk to close.

[0010] Optionally, controlling at least one of the vehicle's door unlocking, window opening, sunroof opening, and trunk opening includes: if the rollover completion probability is greater than a preset probability, controlling at least one of the vehicle's door unlocking, window opening, sunroof opening, and trunk opening after a preset delay.

[0011] Optionally, controlling at least one of the vehicle's door unlocking, window opening, sunroof opening, and trunk opening after a preset delay includes: obtaining the rollover end probability at each moment within the preset time; if the rollover end probability at each moment is greater than a preset probability, then controlling at least one of the vehicle's door unlocking, window opening, sunroof opening, and trunk opening; if the rollover end probability at any moment within the preset time is less than or equal to a preset probability, then controlling the vehicle's door locking, window closing, sunroof closing, and trunk closing.

[0012] Optionally, before calculating the rollover termination probability of the vehicle based on the angular velocity and acceleration, the method further includes: at the moment the vehicle rollover is triggered, controlling the vehicle's airbags to ignite, the high voltage to be cut off, an emergency call signal to be sent, and the hazard lights to be turned on.

[0013] A second aspect of this application provides a vehicle rollover protection device, comprising: an acquisition module for acquiring the angular velocity in a target direction and the acceleration in multiple directions of a vehicle during a rollover; a calculation module for calculating the rollover termination probability of the vehicle based on the angular velocity and the acceleration; and a control module for controlling the vehicle to perform a rollover protection action based on the rollover termination probability.

[0014] Optionally, the formula for calculating the roll-off end probability is:

[0015]

[0016] Where y is the probability that the roll has ended at the current moment, and χ = [ω x θ x θ x 2 +ω x 2 α y α z ], where ω x Let θ be the angular velocity of the vehicle around the x-axis. x For ω x From the perspective of obtaining the integral, α y Let α be the acceleration of the vehicle about the y-axis. z Let K be the vehicle's acceleration around the z-axis. K and b are model parameters for the current vehicle model, where K = [K1, K2, K3, K4, K5].

[0017] Optionally, the first control module is further configured to: if the rollover completion probability is greater than a preset probability, control at least one of the following functions of the vehicle: unlocking the doors, opening the windows, opening the sunroof, and opening the trunk; if the rollover completion probability is less than or equal to the preset probability, control the following functions of the vehicle: locking the doors, closing the windows, closing the sunroof, and closing the trunk.

[0018] Optionally, the first control module is further configured to: control at least one of the following functions of unlocking the vehicle doors, opening the windows, opening the sunroof, and opening the trunk after a preset delay.

[0019] Optionally, the first control module is further configured to: obtain the rollover end probability at each moment within a preset duration; if the rollover end probability at each moment is greater than the preset probability, control at least one of the following actions: unlocking the vehicle doors, opening the windows, opening the sunroof, and opening the trunk; if the rollover end probability at any moment within the preset duration is less than or equal to the preset probability, control the following actions: locking the vehicle doors, closing the windows, closing the sunroof, and closing the trunk.

[0020] Optionally, it also includes: a second control module for controlling the vehicle's airbag ignition, high-voltage power-off, sending an emergency call signal, and activating hazard lights when the vehicle rollover is triggered.

[0021] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle rollover protection method as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the vehicle rollover protection method as described in the above embodiments.

[0023] A fifth aspect of this application provides a computer program product, including a computer program, which, when executed, is used to implement the vehicle rollover protection method as described in the above embodiments.

[0024] Therefore, this application has at least the following beneficial effects:

[0025] The embodiments of this application can calculate the rollover termination probability of a vehicle based on its angular velocity and acceleration in a rollover situation; by controlling the vehicle to perform rollover protection actions based on the rollover termination probability, the problem of users suffering secondary injuries in a collision due to improper timing of vehicle unlocking can be avoided, thereby improving vehicle safety and enhancing user experience.

[0026] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0027] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0028] Figure 1 This is a flowchart of a vehicle rollover protection method according to an embodiment of this application;

[0029] Figure 2 This is a schematic diagram of the novel adaptive unlocking process under rolling conditions provided in the embodiments of this application;

[0030] Figure 3 This is a schematic diagram of the algorithm for determining the end of a roll according to an embodiment of this application;

[0031] Figure 4 This is a block diagram of a vehicle rollover protection device according to an embodiment of this application;

[0032] Figure 5 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0033] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein 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 intended to explain this application, and should not be construed as limiting this application.

[0034] In related technologies, during high-speed rollovers, even after the airbags deploy and the doors unlock simultaneously, the vehicle will continue to roll at high speed for a period of time. If the vehicle's acceleration reaches 35g or more, the doors are likely to be flung off, making occupants more vulnerable to impacts from external obstacles. This could even cause hands, heads, or other parts of the body to be thrown out of the vehicle's frame and suffer greater injuries. Therefore, in rollover situations, the strategy of unlocking the doors simultaneously with airbag deployment has low applicability and poor safety.

[0035] This application uses signals from a five-axis yaw angle sensor to determine the state of a vehicle after it has rolled over. During the rollover, the doors are kept locked to prevent them from opening and causing external impact injuries to the occupants. When the rollover ends, the doors are unlocked to allow outside personnel to rescue the occupants more quickly.

[0036] This application uses a logistic regression-based algorithm to build a model to determine whether the rollover has ended. Without increasing hardware or the workload of project data collection, by optimizing the unlocking strategy through software logic and adding a logistic regression-based algorithm to determine the end of the rollover, the risk of the car door opening due to door unlocking during the rollover process can be eliminated, thus better protecting the safety of the occupants.

[0037] The following description, with reference to the accompanying drawings, outlines a vehicle rollover protection method, apparatus, vehicle, storage medium, and program product according to embodiments of this application. Specifically, Figure 1 This is a schematic flowchart of a vehicle rollover protection method provided in an embodiment of this application.

[0038] like Figure 1 As shown, the vehicle rollover protection method includes the following steps:

[0039] In step S101, the angular velocity in the target direction and the acceleration in multiple directions of the vehicle during the rollover are obtained.

[0040] It is understood that the embodiments of this application can obtain the angular velocity, acceleration, y-axis and z-axis of the vehicle in the rollover state through a five-axis yaw angle sensor, so as to calculate the probability of the vehicle's rollover termination based on the angular velocity and acceleration in multiple directions.

[0041] It should be noted that the target direction is the vehicle's x-axis direction. Before using the five-axis yaw angle sensor to obtain the vehicle's angular velocity, acceleration, y-axis acceleration, and z-axis acceleration in the x-axis direction, it is necessary to establish a vehicle coordinate system and determine the x-axis, y-axis, and z-axis based on the vehicle coordinate system, so as to obtain the vehicle's angular velocity in the target direction and acceleration in multiple directions during rollover.

[0042] In this embodiment of the application, before calculating the probability of the vehicle rolling over based on angular velocity and acceleration, the method further includes: at the moment when the vehicle rollover is triggered, controlling the vehicle's airbags to ignite, the high voltage to be cut off, sending an emergency call signal, and turning on the hazard lights.

[0043] It is understood that, in the embodiments of this application, the airbags of the vehicle can be ignited, the high voltage is cut off, an emergency call signal is sent, and the hazard lights are turned on when the vehicle rollover is triggered, so as to ensure the safety of the people in the vehicle and the timeliness of rescue.

[0044] It should be noted that when a vehicle experiences a collision and the airbags deploy, the airbag control unit uses internal sensors to determine whether it is a rollover situation. If it is not a rollover situation, it sends out the first control signal and the second control signal together, and simultaneously executes the actions of airbag deployment, high voltage de-energization, sending an emergency call signal, and unlocking the doors.

[0045] If the current collision event is determined to be a rollover, when the rollover signal reaches the airbag deployment threshold, a first control signal is issued to execute the actions of airbag deployment, high voltage power-off, and sending an emergency call signal. However, the second control signal is not issued yet, and the doors are not unlocked to prevent the doors from automatically opening due to excessive acceleration during the subsequent rollover. The first control signal is used to control the vehicle to execute the actions of airbag deployment, high voltage power-off, and sending an emergency call signal, while the second control signal is used to control at least one of the vehicle's door unlocking, window opening, sunroof opening, and trunk opening.

[0046] In step S102, the probability of the vehicle ending its rollover is calculated based on the angular velocity and acceleration.

[0047] Furthermore, the formula for calculating the probability of the roll ending is:

[0048]

[0049] Where y is the probability that the roll has ended at the current moment, and χ = [ω x θ x θ x 2 +ω x 2 α y α z ], where ω x Let θ be the angular velocity of the vehicle around the x-axis. x For ω x From the perspective of obtaining the integral, α y Let α be the acceleration of the vehicle along the y-axis. z Let K be the vehicle's acceleration along the z-axis. K and b are model parameters for the current vehicle model. K = [K1, K2, K3, K4, K5].

[0050] It is understood that the embodiments of this application can calculate the probability of the vehicle's rollover ending based on the angular velocity of the x-axis, the acceleration of the y-axis, and the acceleration of the z-axis. This improves the overall efficiency and accuracy of the processing by optimizing the unlocking strategy through software logic and adding a logistic regression-based judgment on the probability of the rollover ending without increasing hardware or the workload of project data collection.

[0051] It should be noted that in the actual project development process, it is necessary to collect data on rollover conditions for each vehicle model to determine the parameters K and b in the algorithm. This includes collecting signals from various conditions such as collision with curbs, rollovers on sand, and spiral rollovers. The collected signals include ω. x α y and α z .

[0052] The aforementioned data acquisition can be performed concurrently with the data acquisition for rollover point detonation calibration, thus not increasing the workload or cost of project development. The signal acquisition frequency is typically 10000Hz. The signal is down-clocked to 100Hz to meet the computational load requirements of the airbag electronic control unit. The characteristic quantity, angular velocity ω around the vehicle's x-axis, is extracted from the signal at each time point after frequency down-clocking. x Angle θ x The sum of the squares of the two, θ x 2 +ω x 2 acceleration α along the y-axis y and acceleration α along the z-axis z The input χ is then low-pass filtered to obtain the input χ for training the logistic regression algorithm model. i Based on the high-speed video footage collected during the experiment, the results at each sampling time point after frequency reduction were labeled. This involved manually determining whether the tumbling had ended at that time point, thus obtaining another label input y for model training. i χ at each time point after frequency reduction i and y i All parameters are input into the model for training, and finally the model parameters K and b suitable for this vehicle model project are obtained.

[0053] In step S103, the vehicle is controlled to perform a rollover protection action based on the rollover end probability.

[0054] It is understood that the embodiments of this application can control the vehicle to perform rollover protection actions based on the rollover completion probability, which can avoid the problem of users suffering secondary injuries in a collision due to improper timing of vehicle unlocking, thereby improving vehicle safety and enhancing user experience.

[0055] In this embodiment of the application, controlling the vehicle to perform rollover protection actions based on the rollover end probability includes: if the rollover end probability is greater than a preset probability, controlling at least one of the vehicle's doors to unlock, windows to open, sunroof to open, and trunk to open; if the rollover end probability is less than or equal to the preset probability, controlling the vehicle's doors to lock, windows to close, sunroof to close, and trunk to close.

[0056] The preset probability can be 0.5, and can be set according to actual needs without specific limitations.

[0057] It is understood that, in this embodiment of the application, if the probability of rollover completion is greater than a preset probability, at least one of the following functions is controlled: unlocking the vehicle doors, opening the windows, opening the sunroof, and opening the trunk. If the probability of rollover completion is less than or equal to the preset probability, the following functions are controlled: locking the vehicle doors, closing the windows, closing the sunroof, and closing the trunk. This can avoid the problem of users suffering secondary injuries in a collision due to improper timing of vehicle unlocking, thereby improving vehicle safety and enhancing user experience.

[0058] It should be noted that in the logistic regression-based algorithm of this application, U∈{0,1} is set to:

[0059]

[0060] Specifically, the algorithm determines the roll to be complete only when the probability of the roll ending is greater than 0.5.

[0061] In this embodiment of the application, controlling at least one of the following functions of a vehicle—unlocking the doors, opening the windows, opening the sunroof, and opening the trunk—includes: controlling at least one of the following functions after a preset delay.

[0062] The preset duration can be approximately 2 seconds after the roll ends, and can be set according to actual needs without specific limitations.

[0063] It is understood that the embodiments of this application may delay for a preset period of time before controlling at least one of the vehicle door unlocking, window opening, sunroof opening and trunk opening, in order to prevent the user from suffering secondary injury in the collision if the collision has not ended, thereby improving vehicle safety and enhancing user experience.

[0064] In this embodiment of the application, controlling at least one of the following actions after a preset delay time: unlocking the vehicle door, opening the window, opening the sunroof, and opening the trunk, includes: obtaining the rollover end probability at each moment within the preset time; if the rollover end probability at each moment is greater than the preset probability, then controlling at least one of the following actions: unlocking the vehicle door, opening the window, opening the sunroof, and opening the trunk; if the rollover end probability at any moment within the preset time is less than or equal to the preset probability, then controlling the vehicle door to lock, closing the window, closing the sunroof, and closing the trunk.

[0065] It is understood that, in the embodiments of this application, if the probability of the rollover ending after a preset time is greater than the preset probability, then control at least one of the following actions: unlock the vehicle door, open the window, open the sunroof, and open the trunk. Otherwise, control the following actions: lock the vehicle door, close the window, close the sunroof, and close the trunk. This is to prevent secondary injuries to the user during the collision if the collision does not end, thereby improving vehicle safety and enhancing the user experience.

[0066] It should be noted that, due to the longer collision time compared to conventional frontal, side, and rear collisions, and considering the computational load on the airbag control unit, feature values ​​are sampled every 10ms and input into the logistic regression algorithm for calculation. Let the current time be i, and the result calculated based on the logistic regression algorithm be U. i , when U i U i+1, U i+2 , ..., U i+200 When all values ​​are 1, meaning for 201 consecutive feature inputs, the algorithm outputs a probability greater than 0.5 before determining that the roll has ended. Figure 3 As shown.

[0067] Specifically, during the labeling process, high-speed camera video is used to manually mark the vehicle's dynamic balance state as "roll not yet finished" and the actual roll finished state as "roll finished." Therefore, the trained model can effectively distinguish between the dynamic balance state and the actual roll finished state. Furthermore, this invention incorporates an image stabilization design, requiring the algorithm to continuously output U 201 times. i Only when both values ​​are 1 is the rollover considered complete. This effectively avoids false recognition and prevents the doors from unlocking during the vehicle's dynamic balance process, which could increase the risk of injury to occupants.

[0068] According to the vehicle rollover protection method proposed in this application, the probability of rollover termination of the vehicle is calculated based on the angular velocity and acceleration of the vehicle in the rollover situation; the vehicle is controlled to perform rollover protection actions based on the rollover termination probability, which can avoid the problem of secondary injury to the user in a collision caused by improper timing of vehicle unlocking, thereby improving vehicle safety and enhancing user experience.

[0069] The following will combine Figure 3 The vehicle rollover protection method described in this application is explained in detail, and the specific steps are as follows:

[0070] Step 1: When a vehicle is involved in a collision and the airbags deploy, the airbag control unit uses internal sensors to determine whether it is a rollover situation. If it is not a rollover situation, it sends out the first control signal and the second control signal together, and simultaneously executes the actions of airbag deployment, high voltage power-off, emergency call for rescue signal and door unlocking.

[0071] Step 2: The airbag electronic control unit determines that the current collision event is a rollover. When the rollover signal reaches the airbag deployment threshold, it sends out the first control signal to execute the actions of airbag deployment, high voltage power-off, and emergency rescue call. However, the second control signal is not sent out yet, and the door is not unlocked to prevent the door from opening automatically due to excessive acceleration during the subsequent rollover.

[0072] Step 3: When the vehicle rollover ends, the airbag control unit uses the signal input from the five-axis yaw angle sensor and the algorithm to determine that the vehicle has finished rolling. At this time, the airbag control unit sends a second control signal. After receiving the second control signal, the IBCM (Intelligent Body Control Module) performs an unlocking operation on the unlocking mechanism to ensure that rescuers outside the vehicle can open the door in time to rescue the occupants.

[0073] For the algorithm to determine whether a rollover has ended, since the five-axis yaw angle sensor will have some zero drift, and the vehicle may reach a state of dynamic equilibrium during the rollover process, which is similar to the state at the end of the rollover, it is easy to be misidentified. Therefore, this invention adopts an algorithm based on logistic regression to build a model to determine whether the rollover has ended.

[0074] The angular velocity values ​​of a vehicle are relatively small and difficult to distinguish between its dynamic equilibrium state during rollover and its final rollover state. Therefore, for the feature quantities of logistic regression algorithms, this invention extracts the angular velocity ω around the vehicle's x-axis after low-pass filtering. x Angle θ x The sum of the squares of the two, θ x 2 +ω x 2 acceleration α along the y-axis y and acceleration α along the z-axis z As a characteristic quantity, where ω x α y and α zThe yaw angle is directly obtained through a five-axis yaw sensor, while θ needs to be obtained by integrating ω. Therefore, the input to the algorithm is the vector χ = [ω]. x θ x θ x 2 +ω x 2 α y α z According to the logistic regression algorithm model, the output y is...

[0075]

[0076] Where K = [K1, K2, K3, K4, K5], K and b are model parameters of the current vehicle type, and the output y is the probability of the rollover ending, y∈[0,1]. Only K and b need to be determined to use this algorithm to calculate the probability of whether the rollover has ended at the current moment. Then, in the algorithm, U∈{0,1} is set to:

[0077]

[0078] Because rollover collisions have a longer impact time compared to conventional frontal, side, and rear collisions, and considering the computational load on the airbag control unit, feature values ​​are sampled every 10ms and input into the logistic regression algorithm for calculation. Let the current time be i, and the result calculated based on the logistic regression algorithm be U. i , when U i U i+1, U i+2 , ..., U i+200 When all values ​​are 1, meaning for 201 consecutive feature inputs, the algorithm outputs a probability greater than 0.5 before determining that the roll has ended. Figure 3 As shown.

[0079] It should be noted that in the actual project development process, it is necessary to collect data on rollover conditions for each vehicle model to determine the parameters K and b in the algorithm. This includes collecting signals from various conditions such as collision with curbs, rollovers on sand, and spiral rollovers. The collected signals include ω. x α y and α z .

[0080] The aforementioned data acquisition can be performed concurrently with the data acquisition for rollover point detonation calibration, thus not increasing the workload or cost of project development. The signal acquisition frequency is typically 10000Hz. The signal is down-clocked to 100Hz to meet the computational load requirements of the airbag electronic control unit. The characteristic quantity, angular velocity ω around the vehicle's x-axis, is extracted from the signal at each time point after frequency down-clocking. xAngle θ x The sum of the squares of the two, θ x 2 +ω x 2 y-axis acceleration α y and z-axis acceleration α z The input χ is then low-pass filtered to obtain the input χ for training the logistic regression algorithm model. i Based on the high-speed video footage collected during the experiment, the results at each sampling time point after frequency reduction were labeled. This involved manually determining whether the tumbling had ended at that time point, thus obtaining another label input y for model training. i χ at each time point after frequency reduction i and y i All parameters are input into the model for training, and finally the model parameters K and b suitable for this vehicle model project are obtained.

[0081] During the labeling process, high-speed camera video is used to manually mark the vehicle's dynamic balance state as "roll not yet finished" and the actual roll finished state as "roll finished." Therefore, the trained model can effectively distinguish between the dynamic balance state and the actual roll finished state. Furthermore, this invention incorporates image stabilization, requiring the algorithm to continuously output U 201 times. i Only when both values ​​are 1 is the rollover considered complete. This effectively avoids false recognition and prevents the doors from unlocking during the vehicle's dynamic balance process, which could increase the risk of injury to occupants.

[0082] In summary, based on the signals collected by the five-axis yaw angle sensor, a rollover termination judgment algorithm based on logistic regression was designed to accurately identify whether the vehicle rollover has ended. By optimizing the system's software logic, adaptive unlocking in the rollover condition was achieved, ensuring that the vehicle will not automatically unlock during the rollover process, preventing the door from automatically opening during the rollover and protecting the safety of the occupants. At the same time, it can unlock in time when the rollover ends, ensuring that the occupants can receive timely rescue after the rollover. Therefore, for vehicles with rollover ignition function, this application, without increasing hardware or project data collection workload, can eliminate the risk of the door opening due to door unlocking during the rollover process by optimizing the unlocking strategy through software logic and adding a logistic regression-based rollover termination judgment algorithm, thus better protecting the safety of the occupants.

[0083] Next, the vehicle rollover protection device proposed according to the embodiments of this application is described with reference to the accompanying drawings.

[0084] Figure 4 This is a block diagram of a vehicle rollover protection device according to an embodiment of this application.

[0085] like Figure 4As shown, the vehicle rollover protection device 10 includes: an acquisition module 100, a calculation module 200, and a control module 300.

[0086] The acquisition module 100 is used to acquire the angular velocity in the target direction and the acceleration in multiple directions of the vehicle in the event of a rollover; the calculation module 200 is used to calculate the rollover termination probability of the vehicle based on the angular velocity and acceleration; and the first control module 300 is used to control the vehicle to perform a rollover protection action based on the rollover termination probability.

[0087] In this embodiment of the application, the formula for calculating the rollover end probability is:

[0088]

[0089] Where y is the probability that the roll has ended at the current moment, and χ = [ω x θ x θ x 2 +ω x 2 α y α z ], where ω x Let θ be the angular velocity of the vehicle around the x-axis. x For ω x From the perspective of obtaining the integral, α y Let α be the acceleration of the vehicle along the y-axis. z Let K be the vehicle's acceleration along the z-axis. K and b are model parameters for the current vehicle model. K = [K1, K2, K3, K4, K5].

[0090] In this embodiment of the application, the first control module 300 is further configured to: if the rollover end probability is greater than a preset probability, control at least one of the following functions of the vehicle: unlocking the doors, opening the windows, opening the sunroof, and opening the trunk; if the rollover end probability is less than or equal to the preset probability, control the following functions of the vehicle: locking the doors, closing the windows, closing the sunroof, and closing the trunk.

[0091] In this embodiment, the first control module 300 is further configured to: control at least one of the following functions of unlocking the vehicle door, opening the window, opening the sunroof, and opening the trunk after a preset delay time.

[0092] In this embodiment of the application, the first control module 300 is further configured to: obtain the rollover end probability at each moment within a preset duration; if the rollover end probability at each moment is greater than the preset probability, control at least one of the following actions: unlocking the vehicle door, opening the window, opening the sunroof, and opening the trunk; if the rollover end probability at any moment within the preset duration is less than or equal to the preset probability, control the following actions: locking the vehicle door, closing the window, closing the sunroof, and closing the trunk.

[0093] In this embodiment of the application, it further includes: a second control module, used to control the vehicle's airbag ignition, high voltage power-off, sending an emergency call signal and activating hazard lights when the vehicle rollover is triggered.

[0094] It should be noted that the foregoing explanation of the vehicle rollover protection method embodiment also applies to the vehicle rollover protection device of this embodiment, and will not be repeated here.

[0095] According to the vehicle rollover protection device proposed in this application embodiment, the probability of rollover termination of the vehicle is calculated based on the angular velocity and acceleration of the vehicle in the rollover situation; the vehicle is controlled to perform rollover protection action based on the rollover termination probability, which can avoid the problem of secondary injury to the user in the collision caused by improper timing of vehicle unlocking, thereby improving vehicle safety and enhancing user experience.

[0096] Figure 5 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0097] The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0098] When processor 502 executes the program, it implements the vehicle rollover protection method provided in the above embodiments.

[0099] Furthermore, the vehicle also includes:

[0100] Communication interface 503 is used for communication between memory 501 and processor 502.

[0101] The memory 501 is used to store computer programs that can run on the processor 502.

[0102] The memory 501 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0103] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. 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 address bus, data bus, control bus, etc. For ease of representation,Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0104] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0105] Processor 502 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0106] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the vehicle rollover protection method described above.

[0107] This application also provides a computer program product, which, when executed, is used to implement the vehicle rollover protection method as described in the above embodiments.

[0108] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0109] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0110] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0111] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0112] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0113] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for protecting a vehicle from rollover, characterized in that, Includes the following steps: Obtain the angular velocity in the target direction and the acceleration in multiple directions of the vehicle during a rollover. The rollover termination probability of the vehicle is calculated based on the angular velocity and the acceleration, wherein the rollover termination probability is calculated based on a trained logistic regression algorithm model and is used to represent the probability of the rollover terminating at the current moment. Controlling the vehicle to perform rollover protection actions based on the rollover end probability includes: if the rollover end probability is greater than a preset probability, controlling at least one of the vehicle's doors to unlock, windows to open, sunroof to open, and trunk to open; if the rollover end probability is less than or equal to the preset probability, controlling the vehicle's doors to lock, windows to close, sunroof to close, and trunk to close.

2. The vehicle rollover protection method according to claim 1, characterized in that, The formula for calculating the roll completion probability is: ， Where y is the probability that the roll has ended at the current moment. ,in, Let be the angular velocity of the vehicle around the x-axis. To From the perspective of points acquisition, Let the vehicle's acceleration be along the y-axis. Let K be the vehicle's acceleration along the z-axis, and let K and b be model parameters for the current vehicle model. .

3. The vehicle rollover protection method according to claim 1, characterized in that, At least one of the functions controlling the unlocking of the vehicle doors, opening of the windows, opening of the sunroof, and opening of the trunk includes: If the probability of the rollover ending is greater than a preset probability, after a preset delay, control at least one of the following actions: unlock the vehicle door, open the window, open the sunroof, and open the trunk.

4. The vehicle rollover protection method according to claim 3, characterized in that, The function of controlling at least one of the vehicle's door unlocking, window opening, sunroof opening, and trunk opening after a preset delay time includes: Obtain the probability of the roll ending at each moment within the preset duration; If the probability of the rollover ending at each moment is greater than the preset probability, then control at least one of the following actions: unlocking the vehicle door, opening the window, opening the sunroof, and opening the trunk. If the probability of the rollover ending at any moment within the preset time period is less than or equal to the preset probability, then the vehicle doors, windows, sunroof, and trunk are controlled to lock.

5. The vehicle rollover protection method according to claim 1, characterized in that, Before calculating the rollover termination probability of the vehicle based on the angular velocity and acceleration, the method further includes: At the moment the vehicle rollover is triggered, the system controls the vehicle's airbags to ignite, the high voltage to be cut off, an emergency call signal to be sent, and the hazard lights to be activated.

6. A vehicle rollover protection device, characterized in that, include: The acquisition module is used to acquire the angular velocity in the target direction and the acceleration in multiple directions of the vehicle during a rollover. The calculation module is used to calculate the rollover termination probability of the vehicle based on the angular velocity and the acceleration, wherein the rollover termination probability is calculated based on a trained logistic regression algorithm model and is used to represent the probability of the rollover terminating at the current moment. The first control module is used to control the vehicle to perform rollover protection actions based on the rollover end probability, wherein controlling the vehicle to perform rollover protection actions based on the rollover end probability includes: if the rollover end probability is greater than a preset probability, controlling at least one of the vehicle's doors to unlock, windows to open, sunroof to open, and trunk to open; if the rollover end probability is less than or equal to the preset probability, controlling the vehicle's doors to lock, windows to close, sunroof to close, and trunk to close.

7. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the vehicle rollover protection method as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the vehicle rollover protection method as described in any one of claims 1-5.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed, it is used to implement the vehicle rollover protection method according to any one of claims 1-5.

Images