Vehicle air bag restraint system explosion control method and device, electronic equipment and program product

Abstract

The invention discloses a vehicle airbag ignition control method and device, electronic equipment and a program product. The method comprises the following steps: acquiring acceleration time sequence data of a plurality of preset positions of a vehicle, air pressure time sequence data of a plurality of preset cavities and environment image time sequence data around the vehicle; according to the acceleration time sequence data, the air pressure time sequence data and the environment image time sequence data, determining a collision risk index and a corresponding target collision part and a target collision angle; when the collision risk index is greater than or equal to a preset first threshold value, inputting the target collision part, the target collision angle and the vehicle speed into a pre-trained airbag explosion time prediction model to obtain an airbag explosion control time sequence; and main air bag explosion control, side air bag explosion control and safety belt pre-tightening control are carried out according to the air bag explosion control time sequence. According to the method, the safety air bag explosion control accuracy is improved, so that the driving safety of the vehicle is improved, and the method can be applied to the technical field of vehicle control.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a method, device, electronic equipment, and program product for controlling the deployment of vehicle airbags. Background Technology

[0002] Current vehicle airbag systems primarily consist of collision sensors installed at the front, sides, and rear of the vehicle, along with the airbag system control unit (SRS ECU). In the event of a collision, the system relies solely on these existing sensors and the SRS ECU to determine the impact. Collisions that avoid the sensor mounting points (such as those involving driving through obstacles) can prevent airbag deployment, compromising vehicle safety. Furthermore, the acceleration or impact force detected by the collision sensors must reach a certain threshold to trigger deployment, which can also lead to situations where a collision occurs but the airbags fail to deploy, similarly impacting vehicle safety.

[0003] The above problems urgently need to be addressed. Summary of the Invention

[0004] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0005] Therefore, one objective of this invention is to provide a vehicle airbag deployment control method. This method determines a collision risk index based on acceleration time-series data at different vehicle locations, air pressure time-series data in different cavities, and environmental image time-series data surrounding the vehicle. When the collision risk index exceeds a threshold, it predicts the optimal airbag deployment control timing based on the collision location, collision angle, and vehicle speed, thereby improving the accuracy of airbag deployment control and thus enhancing vehicle passenger safety.

[0006] Another objective of this invention is to provide a vehicle airbag deployment control device.

[0007] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include: On one hand, embodiments of the present invention provide a method for controlling the deployment of vehicle airbags, comprising the following steps: Acquire acceleration time-series data at multiple preset locations of the vehicle, air pressure time-series data at multiple preset cavities, and environmental image time-series data around the vehicle; The collision risk index, the corresponding target collision location, and the target collision angle are determined based on the acceleration time-series data, the air pressure time-series data, and the environmental image time-series data. When the collision risk index is greater than or equal to a preset first threshold, the target collision location, the target collision angle, and the vehicle speed are input into a pre-trained airbag deployment timing prediction model to obtain the airbag deployment control timing sequence. The main airbag deployment control, side airbag deployment control, and seat belt pretensioning control are performed according to the airbag deployment control sequence.

[0008] Furthermore, in one embodiment of the present invention, the acquisition of acceleration time-series data at multiple preset positions of the vehicle, air pressure time-series data at multiple preset cavities, and environmental image time-series data around the vehicle specifically includes: The acceleration timing data is obtained by collision sensors installed at the front end, sides, rear end, front side reinforcement beam, longitudinal beam, sill beam, and hood of the vehicle body. The air pressure timing data is obtained by air pressure sensors installed in the cavity of the front bulkhead side reinforcing beam, the cavity of the front longitudinal beam, the cavity of the sill beam, and the cavity of the engine compartment. The environmental image time-series data is acquired by cameras installed around the vehicle body.

[0009] Furthermore, in one embodiment of the present invention, the step of determining the collision risk index and the corresponding target collision location and target collision angle based on the acceleration time-series data, the air pressure time-series data, and the environmental image time-series data specifically includes: The instantaneous acceleration at each preset position is determined based on the acceleration time-series data, and the first collision risk value at the corresponding preset position is determined based on the instantaneous acceleration. The instantaneous air pressure change rate of each preset cavity is determined based on the air pressure time series data, and the second collision risk value of the corresponding preset cavity is determined based on the instantaneous air pressure change rate. The current collision scene and current collision angle are identified based on the environmental image time series data, and the corresponding collision identification confidence level is determined. Then, a third collision risk value is determined based on the collision identification confidence level. The collision risk index is obtained by weighting and summing the maximum value of the first collision risk value, the maximum value of the second collision risk value, and the third collision risk value according to a preset first weighting coefficient. The target collision location is determined based on the preset location corresponding to the maximum value of the first collision risk value and the preset cavity corresponding to the maximum value of the second collision risk value. The target collision angle is determined based on the vehicle's body posture and the current collision angle.

[0010] Furthermore, in one embodiment of the present invention, the airbag deployment time prediction model is trained through the following steps: The sample collision location, sample collision angle, and sample vehicle speed of the test vehicle are obtained, and the corresponding airbag deployment timing labels are determined by manual annotation. The collision location, collision angle, and vehicle speed of the sample are input into a pre-built deep neural network to obtain the airbag deployment prediction timeline. The loss value is calculated based on the airbag detonation prediction timeline and the airbag detonation timeline label. The parameters of the deep neural network are updated using the backpropagation algorithm based on the loss value to obtain the trained airbag detonation time prediction model. The airbag deployment timing labels include main airbag deployment timing labels, side airbag deployment timing labels, seatbelt pretensioning timing labels, and corresponding control sequence labels.

[0011] Furthermore, in one embodiment of the present invention, the step of calculating the loss value based on the airbag detonation prediction timeline and the airbag detonation timeline tag specifically includes: The predicted timing of main airbag deployment, side airbag deployment, seat belt pretensioning, and corresponding prediction control sequence are determined based on the airbag deployment prediction timing. A first time deviation loss is determined based on the predicted time of main airbag deployment and the main airbag deployment time label; a second time deviation loss is determined based on the predicted time of side airbag deployment and the side airbag deployment time label; and a third time deviation loss is determined based on the predicted time of seat belt pretensioning and the seat belt pretensioning time label. The sequence deviation loss is determined based on the predicted control sequence and the control sequence label; The first time deviation loss, the second time deviation loss, the third time deviation loss, and the sequence deviation loss are weighted and summed according to a preset second weighting coefficient to obtain the loss value.

[0012] Furthermore, in one embodiment of the present invention, the step of controlling the main airbag deployment, the side airbag deployment, and the seatbelt pretensioning according to the airbag deployment control timing specifically includes: The timing of the target main airbag deployment, the timing of the target side airbag deployment, and the timing of the target seatbelt pretensioning are determined according to the airbag deployment control timing sequence. The main airbag deployment is controlled according to the target main airbag deployment time, the side airbag deployment is controlled according to the target side airbag deployment time, and the seat belt pretensioning is controlled according to the target seat belt pretensioning time.

[0013] Furthermore, in one embodiment of the present invention, the vehicle airbag deployment control method further includes: The acceleration time-series data, the air pressure time-series data, and the environmental image time-series data are uploaded to the cloud.

[0014] On the other hand, embodiments of the present invention provide a vehicle airbag deployment control device, comprising: The data acquisition module is used to acquire acceleration time-series data at multiple preset locations of the vehicle, air pressure time-series data at multiple preset cavities, and environmental image time-series data around the vehicle. The collision risk identification module is used to determine the collision risk index and the corresponding target collision location and target collision angle based on the acceleration time-series data, the air pressure time-series data and the environmental image time-series data. The airbag deployment prediction module is used to input the target collision location, the target collision angle, and the vehicle speed into a pre-trained airbag deployment timing prediction model when the collision risk index is greater than or equal to a preset first threshold, so as to obtain the airbag deployment control timing sequence. The airbag deployment control module is used to control the main airbag deployment, the side airbag deployment, and the seat belt pretensioning according to the airbag deployment control timing.

[0015] On the other hand, embodiments of the present invention provide an electronic device, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-described vehicle airbag deployment control method.

[0016] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described vehicle airbag deployment control method.

[0017] On the other hand, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the above-described vehicle airbag deployment control method.

[0018] The advantages and beneficial effects of the present invention 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 the invention: This invention acquires acceleration time-series data from multiple preset locations of the vehicle, air pressure time-series data from multiple preset cavities, and environmental image time-series data surrounding the vehicle. Based on these data, a collision risk index, corresponding target collision location, and target collision angle are determined. When the collision risk index is greater than or equal to a preset first threshold, the target collision location, target collision angle, and vehicle speed are input into a pre-trained airbag deployment timing prediction model to obtain the airbag deployment control timing. The main airbag deployment, side airbag deployment, and seatbelt pretensioning are then controlled according to this timing. This invention determines the collision risk index based on acceleration time-series data from different vehicle locations, air pressure time-series data from different cavities, and environmental image time-series data surrounding the vehicle. When the collision risk index exceeds a threshold, the optimal airbag deployment control timing is predicted based on the collision location, collision angle, and vehicle speed, improving the accuracy of airbag deployment control and thus enhancing vehicle passenger safety. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating the steps of a vehicle airbag deployment control method provided in an embodiment of the present invention; Figure 2 This is a structural block diagram of a vehicle airbag deployment control device provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0023] The vehicle airbag deployment control method provided in this invention can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the vehicle airbag deployment control method, but is not limited to the above forms.

[0024] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0025] It should be noted that in various specific embodiments of the present invention, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of the present invention require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to a confirmation page. Only after obtaining the user's separate permission or consent is the necessary user-related data for the normal operation of the embodiments of the present invention acquired.

[0026] Reference Figure 1 This invention provides a method for controlling the deployment of vehicle airbags, specifically including the following steps: S101. Acquire acceleration time-series data of multiple preset positions of the vehicle, air pressure time-series data of multiple preset cavities, and environmental image time-series data around the vehicle. S102. Determine the collision risk index and the corresponding target collision location and target collision angle based on acceleration time series data, air pressure time series data and environmental image time series data. S103. When the collision risk index is greater than or equal to the preset first threshold, the target collision part, the target collision angle and the vehicle speed are input into the pre-trained airbag deployment timing prediction model to obtain the airbag deployment control timing sequence. S104. Perform main airbag deployment control, side airbag deployment control, and seat belt pretensioning control according to the airbag deployment control sequence.

[0027] This invention determines a collision risk index based on acceleration time-series data at different vehicle locations, air pressure time-series data in different cavities, and environmental image time-series data surrounding the vehicle. When the collision risk index exceeds a threshold, it predicts the optimal airbag deployment control timing based on the collision location, collision angle, and vehicle speed, thereby improving the accuracy of airbag deployment control and enhancing vehicle passenger safety.

[0028] As a further optional implementation, acceleration time-series data at multiple preset positions of the vehicle, air pressure time-series data at multiple preset cavities, and environmental image time-series data around the vehicle are acquired, specifically including: S1011. Acceleration timing data is obtained by collision sensors installed at the front end, sides, rear end, front side reinforcement beam, longitudinal beam, sill beam, and engine hood. S1012. Obtain air pressure timing data through air pressure sensors installed in the cavity of the front bulkhead side reinforcing beam, the cavity of the front longitudinal beam, the cavity of the sill beam, and the cavity of the engine compartment. S1013. Acquire environmental image time-series data through camera devices installed around the vehicle body.

[0029] Specifically, in this embodiment of the invention, while using existing front, side, and rear collision sensors and SRS ECU, collision sensors are added to the front side reinforcement beam, longitudinal beam, sill beam, and engine hood. Pressure sensors are added to the cavities of the front side reinforcement beam, front longitudinal beam, sill beam, and engine compartment for auxiliary judgment. In addition, high-definition cameras are installed around the vehicle body, including the fenders, rearview mirrors, front and rear door panels, front and rear bumpers, and front and rear light positions. The entire vehicle uses a backup battery power supply (one for each of the four door panels, and one each for the front engine compartment and rear storage compartment).

[0030] During vehicle operation, acceleration time-series data is acquired through collision sensors located at various preset positions on the vehicle, air pressure time-series data is acquired through air pressure sensors located at various preset cavities on the vehicle, and environmental image time-series data is acquired through camera devices located around the vehicle body. This data will be used for subsequent calculation of the collision risk index.

[0031] As a further optional implementation, a collision risk index, the corresponding target collision location, and the target collision angle are determined based on acceleration time-series data, air pressure time-series data, and environmental image time-series data. Specifically, this includes: S1021. Determine the instantaneous acceleration at each preset position based on the acceleration time sequence data, and determine the first collision risk value at the corresponding preset position based on the instantaneous acceleration. S1022. Determine the instantaneous air pressure change rate of each preset cavity based on the air pressure time sequence data, and determine the second collision risk value of the corresponding preset cavity based on the instantaneous air pressure change rate. S1023. Identify the current collision scene and current collision angle based on the environmental image time series data, determine the corresponding collision identification confidence level, and then determine the third collision risk value based on the collision identification confidence level. S1024. The maximum value of the first collision risk value, the maximum value of the second collision risk value, and the third collision risk value are weighted and summed according to the preset first weighting coefficient to obtain the collision risk index. S1025. Determine the target collision location based on the preset position corresponding to the maximum value of the first collision risk value and the preset cavity corresponding to the maximum value of the second collision risk value. S1026. Determine the target collision angle based on the vehicle's body posture and the current collision angle.

[0032] Specifically, the SRS ECU receives real-time acceleration time-series data, air pressure time-series data, and environmental image time-series data, and calculates the collision risk index through a weighted algorithm, replacing the single threshold judgment of the traditional solution.

[0033] 1. Calculate the first collision risk value based on acceleration time series data. Acceleration time-series data (unit: m / s²) is obtained from collision sensors at multiple preset locations on the vehicle (such as the front of the vehicle, the side of the vehicle, the rear of the vehicle, the front side reinforcement beam, the longitudinal beam, the sill beam, and the engine hood, etc.), with a time granularity typically ranging from 10ms to 100ms.

[0034] For the acceleration time series data at each preset position, take the acceleration value at the current moment as the instantaneous acceleration (noise needs to be filtered out, which can be done by moving average or Kalman filter).

[0035] Based on a preset threshold model (e.g., the risk increases significantly when the acceleration exceeds 50 m / s²), the instantaneous acceleration is converted into a first collision risk value of 0-100. For example: First collision risk value = min[(instantaneous acceleration / maximum safe acceleration) * 100, 100].

[0036] 2. Calculate the second collision risk value based on barometric pressure time series data. Air pressure timing data (unit: kPa) is obtained from air pressure sensors in pre-designed cavities of the vehicle (such as the front bulkhead side reinforcement beam cavity, front longitudinal beam cavity, sill beam cavity, and engine compartment cavity).

[0037] Differentiating the air pressure data yields the instantaneous air pressure change rate (ΔP / Δt, unit: kPa / ms), which reflects the severity of the cavity compression.

[0038] Based on the mapping relationship between air pressure change rate and collision intensity (e.g., risk increases when change rate > 0.5 kPa / ms), it is converted into a second collision risk value of 0-100. For example: Second collision risk value = min[(change rate / maximum safe change rate) * 100, 100].

[0039] 3. Calculate the third collision risk value based on environmental image time series data. Acquire environmental image time-series data from vehicle-mounted cameras (front-view and surround-view) (frame rate is typically 20-30fps).

[0040] The model uses a deep learning model (such as YOLO+RNN) to identify the current collision scenario (such as rear-end collision, side collision, pedestrian collision, etc.) and the collision angle (such as 0° frontal, 90° side). The model outputs the recognition confidence score (0-1), which is directly mapped to the third collision risk value (third collision risk value = confidence score * 100). The higher the confidence score, the higher the risk value.

[0041] 4. Calculate the collision risk index using weighted summation. Preset the first weight coefficient (e.g., acceleration weight 0.4, air pressure weight 0.3, image weight 0.3, which can be adjusted according to the actual scene).

[0042] The maximum value from the first risk value (acceleration risk at the most dangerous location), the maximum value from the second risk value (air pressure risk in the most dangerous cavity), and these values ​​are used together with the third risk value in the calculation: Collision risk index = maximum first risk value * 0.4 + maximum second risk value * 0.3 + maximum third risk value * 0.3.

[0043] 5. Determine the target collision point Find the preset location corresponding to the highest first risk value (such as the left front door) and the preset cavity corresponding to the highest second risk value (such as the left front door cavity). Combine the spatial correlation between the location and the cavity (such as the "left front door" location corresponding to the "left front door cavity") to determine the final target collision location (such as the "left front door area").

[0044] 6. Determine the target collision angle The vehicle's current body attitude (such as pitch angle, roll angle, and yaw angle) is obtained through IMU (Inertial Measurement Unit). The identified current collision angle (relative to the camera view) is combined with the body attitude to convert it into an absolute collision angle (such as the angle relative to the vehicle's longitudinal axis), which is then used as the final target collision angle.

[0045] It can be recognized that when a car goes under the rear of a large truck (which is difficult for current frontal collision sensors to detect), or when a collision occurs that avoids the detection of existing collision sensors, the collision sensors installed on the front side reinforcement beams, longitudinal beams, and hood also capture acceleration data in real time, while the air pressure sensors installed in the corresponding cavities also capture air pressure data in real time. Combined with the environmental image data collected by the camera devices installed around the vehicle body, the SRS ECU can comprehensively judge the current collision risk index and thus activate the airbags to deploy.

[0046] It should be noted that when the collision risk index is greater than or equal to the preset first threshold, the SRS ECU inputs the target collision location, target collision angle, and vehicle speed into the built-in pre-trained airbag deployment timing prediction model to obtain the airbag deployment control timing. In other words, this can correct the seat belt pretensioning and airbag deployment timing based on real-time and comprehensive collision data, and also avoid situations where the airbag fails to deploy or the seat belt fails to pretension due to collision position deviation.

[0047] As an optional implementation, the airbag deployment timing prediction model is trained through the following steps: S201. Obtain the sample collision location, sample collision angle, and sample vehicle speed of the test vehicle, and determine the corresponding airbag deployment timing label through manual annotation. S202. Input the sample collision location, sample collision angle and sample vehicle speed into a pre-built deep neural network to obtain the airbag deployment prediction time series. S203. Calculate the loss value based on the airbag deployment prediction timeline and the airbag deployment timeline label. S204. Update the parameters of the deep neural network based on the loss value using the backpropagation algorithm to obtain the trained airbag detonation time prediction model. The airbag deployment timing labels include the main airbag deployment time label, the side airbag deployment time label, the seat belt pretensioning time label, and the corresponding control sequence label.

[0048] Specifically, the system acquires sample collision locations, collision angles, and vehicle speeds from test vehicles, and manually labels the corresponding airbag deployment timelines. A training dataset is then formed based on a sufficient number of samples. The sample collision locations, collision angles, and vehicle speeds are input into a pre-built deep neural network to obtain the predicted airbag deployment timeline. A loss value is calculated based on the difference between the predicted airbag deployment timeline and the airbag deployment timeline labels. The parameters of the deep neural network are updated using a backpropagation algorithm based on the loss value, completing one round of iterative training. Training stops when the number of iterations reaches a preset threshold or the loss value falls below the preset threshold, resulting in a well-trained airbag deployment time prediction model.

[0049] As a further optional implementation, the loss value is calculated based on the airbag deployment prediction timeline and the airbag deployment timeline tag, specifically including: S2031. Determine the predicted timing of the main airbag deployment, the predicted timing of the side airbag deployment, the predicted timing of the seat belt pretensioning, and the corresponding prediction control sequence based on the airbag deployment prediction timing sequence. S2032. Determine the first time deviation loss based on the predicted time of main airbag deployment and the main airbag deployment time label; determine the second time deviation loss based on the predicted time of side airbag deployment and the side airbag deployment time label; and determine the third time deviation loss based on the predicted time of seat belt pretensioning and the seat belt pretensioning time label. S2033. Determine the sequence deviation loss based on the predicted control sequence and control sequence label; S2034. The first time deviation loss, the second time deviation loss, the third time deviation loss, and the sequence deviation loss are weighted and summed according to the preset second weighting coefficient to obtain the loss value.

[0050] Specifically, both the airbag deployment timing label and the predicted airbag deployment timing output by the model include three key parameters: the deployment time of the main airbag, the deployment time of the side airbags, and the pretensioning time of the seatbelt. The order of these three parameters reflects the control sequence of the main airbag, side airbags, and seatbelt. This embodiment of the invention calculates the loss value from two perspectives: time deviation and sequence deviation.

[0051] For time deviation, the first time deviation loss is determined based on the predicted main airbag deployment time and its label; the second time deviation loss is determined based on the predicted side airbag deployment time and its label; and the third time deviation loss is determined based on the predicted seatbelt pretensioning time and its label. The Smooth L1 loss function can be used as the time deviation loss function.

[0052] For order bias, the order bias loss is determined based on the predicted control order and the control order label. The order bias loss function can use permutation distance (such as Kendall-Tau distance) or cross-entropy loss (treating the order as a classification problem).

[0053] In addition, physical constraint losses can be added; if the prediction order violates physical laws (such as seat belts being predicted after airbags), a high loss value can be directly assigned.

[0054] As a further optional implementation, the main airbag deployment control, side airbag deployment control, and seatbelt pretensioning control are performed according to the airbag deployment control sequence, specifically including: S1041. Determine the timing of the main airbag deployment, the side airbag deployment, and the seatbelt pretensioning based on the airbag deployment control timing sequence. S1042. Control the main airbag deployment based on the target main airbag deployment time, control the side airbag deployment based on the target side airbag deployment time, and control the seat belt pretensioning based on the target seat belt pretensioning time.

[0055] Specifically, by inputting the target collision location, target collision angle, and vehicle speed into a pre-trained airbag deployment timing prediction model to obtain the airbag deployment control timing, the deployment timing of the target main airbag, the deployment timing of the target side airbags, and the pretensioning timing of the target seat belts can be determined. The SRS ECU then performs main airbag deployment control, side airbag deployment control, and seat belt pretensioning control based on these timings.

[0056] As a further optional implementation, the vehicle airbag deployment control method also includes: S105. Upload acceleration time-series data, air pressure time-series data, and environmental image time-series data to the cloud.

[0057] Specifically, when a vehicle collision occurs, a backup power source is used to upload acceleration time-series data, air pressure time-series data, and environmental image time-series data to the cloud, so as to facilitate subsequent collision event reconstruction and vehicle safety performance analysis.

[0058] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention determine the collision risk index based on the acceleration time-series data of different positions of the vehicle, the air pressure time-series data of different cavities, and the environmental image time-series data around the vehicle. When the collision risk index exceeds the threshold, the optimal airbag deployment control timing is predicted based on the collision location, collision angle, and vehicle speed, thereby improving the accuracy of airbag deployment control and thus improving the driving safety of the vehicle.

[0059] Reference Figure 2 This invention provides a vehicle airbag deployment control device, comprising: The data acquisition module is used to acquire acceleration time-series data at multiple preset locations of the vehicle, air pressure time-series data at multiple preset cavities, and environmental image time-series data around the vehicle. The collision risk identification module is used to determine the collision risk index and the corresponding target collision location and target collision angle based on acceleration time-series data, air pressure time-series data and environmental image time-series data. The airbag deployment prediction module is used to input the target collision location, target collision angle and vehicle speed into the pre-trained airbag deployment timing prediction model when the collision risk index is greater than or equal to a preset first threshold, so as to obtain the airbag deployment control timing sequence. The airbag deployment control module is used to control the main airbag deployment, side airbag deployment, and seat belt pretensioning according to the airbag deployment control sequence.

[0060] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0061] Reference Figure 3 This invention provides an electronic device, comprising: At least one processor; At least one memory for storing at least one program; When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned vehicle airbag deployment control method.

[0062] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0063] This invention also provides a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the above-described vehicle airbag deployment control method.

[0064] This invention provides a computer-readable storage medium that can execute a vehicle airbag deployment control method provided in the method embodiments of this invention. It can execute any combination of the implementation steps of the method embodiments and has the corresponding functions and beneficial effects of the method.

[0065] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described vehicle airbag deployment control method.

[0066] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0067] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0068] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0069] The terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0070] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0071] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0072] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0074] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0075] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in 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 a combination 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 (PGAs), field-programmable gate arrays (FPGAs), etc.

[0076] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, 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.

[0077] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0078] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for controlling the deployment of vehicle airbags, characterized in that, Includes the following steps: Acquire acceleration time-series data at multiple preset locations of the vehicle, air pressure time-series data at multiple preset cavities, and environmental image time-series data around the vehicle; The collision risk index, the corresponding target collision location, and the target collision angle are determined based on the acceleration time-series data, the air pressure time-series data, and the environmental image time-series data. When the collision risk index is greater than or equal to a preset first threshold, the target collision location, the target collision angle, and the vehicle speed are input into a pre-trained airbag deployment timing prediction model to obtain the airbag deployment control timing sequence. The main airbag deployment control, side airbag deployment control, and seat belt pretensioning control are performed according to the airbag deployment control sequence.

2. The method for controlling the deployment of a vehicle airbag according to claim 1, characterized in that, The acquisition of acceleration time-series data at multiple preset locations of the vehicle, air pressure time-series data at multiple preset cavities, and environmental image time-series data surrounding the vehicle specifically includes: The acceleration timing data is obtained by collision sensors installed at the front end, sides, rear end, front bulkhead side reinforcement beam, longitudinal beam, sill beam, and engine hood of the vehicle body. The air pressure timing data is obtained by air pressure sensors installed in the cavity of the front bulkhead side reinforcing beam, the cavity of the front longitudinal beam, the cavity of the sill beam, and the cavity of the engine compartment. The environmental image time-series data is acquired by cameras installed around the vehicle body.

3. The method for controlling the deployment of a vehicle airbag according to claim 1, characterized in that, The step of determining the collision risk index and the corresponding target collision location and target collision angle based on the acceleration time-series data, the air pressure time-series data, and the environmental image time-series data specifically includes: The instantaneous acceleration at each preset position is determined based on the acceleration time-series data, and the first collision risk value at the corresponding preset position is determined based on the instantaneous acceleration. The instantaneous air pressure change rate of each preset cavity is determined based on the air pressure time series data, and the second collision risk value of the corresponding preset cavity is determined based on the instantaneous air pressure change rate. The current collision scene and current collision angle are identified based on the environmental image time series data, and the corresponding collision identification confidence level is determined. Then, a third collision risk value is determined based on the collision identification confidence level. The collision risk index is obtained by weighting and summing the maximum value of the first collision risk value, the maximum value of the second collision risk value, and the third collision risk value according to a preset first weighting coefficient. The target collision location is determined based on the preset location corresponding to the maximum value of the first collision risk value and the preset cavity corresponding to the maximum value of the second collision risk value. The target collision angle is determined based on the vehicle's body posture and the current collision angle.

4. The method for controlling the deployment of a vehicle airbag according to claim 1, characterized in that, The airbag deployment timing prediction model is trained through the following steps: The sample collision location, sample collision angle, and sample vehicle speed of the test vehicle are obtained, and the corresponding airbag deployment timing labels are determined by manual annotation. The collision location, collision angle, and vehicle speed of the sample are input into a pre-built deep neural network to obtain the airbag deployment prediction timeline. The loss value is calculated based on the airbag detonation prediction timeline and the airbag detonation timeline label. The parameters of the deep neural network are updated using the backpropagation algorithm based on the loss value to obtain the trained airbag detonation time prediction model. The airbag deployment timing labels include main airbag deployment timing labels, side airbag deployment timing labels, seatbelt pretensioning timing labels, and corresponding control sequence labels.

5. The vehicle airbag deployment control method according to claim 4, characterized in that, The calculation of the loss value based on the airbag deployment prediction timeline and the airbag deployment timeline label specifically includes: The predicted timing of main airbag deployment, side airbag deployment, seat belt pretensioning, and corresponding prediction control sequence are determined based on the airbag deployment prediction timing. A first time deviation loss is determined based on the predicted time of main airbag deployment and the main airbag deployment time label; a second time deviation loss is determined based on the predicted time of side airbag deployment and the side airbag deployment time label; and a third time deviation loss is determined based on the predicted time of seat belt pretensioning and the seat belt pretensioning time label. The sequence deviation loss is determined based on the predicted control sequence and the control sequence label; The first time deviation loss, the second time deviation loss, the third time deviation loss, and the sequence deviation loss are weighted and summed according to a preset second weighting coefficient to obtain the loss value.

6. The method for controlling the deployment of a vehicle airbag according to claim 1, characterized in that, The process of controlling the main airbag deployment, side airbag deployment, and seatbelt pretensioning according to the airbag deployment control sequence specifically includes: The timing of the target main airbag deployment, the timing of the target side airbag deployment, and the timing of the target seatbelt pretensioning are determined according to the airbag deployment control timing sequence. The main airbag deployment is controlled according to the target main airbag deployment time, the side airbag deployment is controlled according to the target side airbag deployment time, and the seat belt pretensioning is controlled according to the target seat belt pretensioning time.

7. A method for controlling the deployment of a vehicle airbag according to any one of claims 1 to 6, characterized in that, The vehicle airbag deployment control method also includes: The acceleration time-series data, the air pressure time-series data, and the environmental image time-series data are uploaded to the cloud.

8. A vehicle airbag deployment control device, characterized in that, include: The data acquisition module is used to acquire acceleration time-series data at multiple preset locations of the vehicle, air pressure time-series data at multiple preset cavities, and environmental image time-series data around the vehicle. The collision risk identification module is used to determine the collision risk index and the corresponding target collision location and target collision angle based on the acceleration time-series data, the air pressure time-series data and the environmental image time-series data. The airbag deployment prediction module is used to input the target collision location, the target collision angle, and the vehicle speed into a pre-trained airbag deployment timing prediction model when the collision risk index is greater than or equal to a preset first threshold, so as to obtain the airbag deployment control timing sequence. The airbag deployment control module is used to control the main airbag deployment, the side airbag deployment, and the seat belt pretensioning according to the airbag deployment control timing.

9. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a vehicle airbag deployment control method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements a vehicle airbag deployment control method as described in any one of claims 1 to 7.

Images