Airbag control method, airbag control device, vehicle, and computer program product

Abstract

The present invention discloses an airbag control method, an airbag control device, a vehicle, and a computer program product. The method comprises: obtaining driving information of a target vehicle, the driving information at least comprising: road information, obstacle information, and collision acceleration, the road information at least comprising road type, the road type at least comprising smooth roads and bumpy roads, the obstacle information at least comprising one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, obstacle types comprising special static obstacles, vulnerable traffic participants, and motor vehicles; using a collision prediction model to process the driving information to obtain fused collision parameters; when it is determined that the fused collision parameters meet preset conditions, generating a control instruction set, the control instruction set being used to control the detonation of the airbag. The present invention solves the technical problem of airbag misexplosion in the related art.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to an airbag control method, an airbag control device, a vehicle, and a computer program product. Background Art

[0002] With the vigorous development of the automobile industry, the number of cars has increased year by year, which will lead to frequent traffic accidents, seriously threatening the safety of life and property. Therefore, people pay more and more attention to automobile safety systems. As a typical representative of automobile safety systems, airbags protect the safety of drivers and passengers by real-time monitoring of collision accidents during vehicle driving and detonating airbags.

[0003] The current airbags obtain acceleration sensor signals in real time and decide whether to deploy the airbags based on whether the calibrated acceleration threshold is reached. However, the existing technology only uses the acceleration signal as a collision parameter to control the airbag control scheme, which may cause the airbag to deploy accidentally in the following conditions: (1) bumpy and rough roads, such as Belgian roads and off-road roads; (2) collisions with static roadblocks, such as sand piles, telephone poles, trash cans, and roadside trees; (3) when the driver closes the door or engine hood forcefully when the vehicle is stationary.

[0004] From the perspective of functional safety, the accidental explosion of airbags not only affects the driver's driving operation but also causes harm to the passengers in the car; on the other hand, it greatly affects the economic efficiency of vehicle maintenance.

[0005] Therefore, in the field of vehicle control in the prior art, how to avoid the accidental explosion of the airbag under bumpy and rough roads, static roadblocks and violent self-vibration conditions has become a key issue. There is currently no effective solution to the above problem. Summary of the invention

[0006] The embodiments of the present invention provide an airbag control method, an airbag control device, a vehicle, and a computer program product to at least solve the technical problem of airbag misexplosion in the related art.

[0007] According to one aspect of an embodiment of the present invention, a method for controlling an airbag is provided, the method comprising the following steps: obtaining driving information of a target vehicle, the driving information comprising at least road information, obstacle information, and collision acceleration, wherein the road information comprises at least road type, and the road type comprises at least smooth roads and bumpy roads, and the obstacle information comprises at least one of the following: obstacle type, obstacle relative distance, obstacle relative speed, and obstacle relative acceleration, and the obstacle type comprises special static obstacles, vulnerable traffic participants, and motor vehicles, and the special static obstacles comprise at least sand piles, electric poles, trash cans, and roadside trees, and the vulnerable traffic participants comprise at least pedestrians and non-motor vehicles; processing the driving information using a collision prediction model to obtain fused collision parameters; and generating a control instruction set when it is determined that the fused collision parameters meet preset conditions, and the control instruction set is used to control the detonation of the airbag.

[0008] Optionally, the driving information is processed using a collision prediction model to obtain fused collision parameters, including the following steps: using the first collision model in the collision prediction model to process obstacle information to obtain first collision parameters; using the second collision model in the collision prediction model to process road information and collision acceleration to obtain second collision parameters; using the fused collision model in the collision prediction model to process the first collision parameters and the second collision parameters to obtain fused collision parameters.

[0009] Optionally, when it is determined that the fusion collision parameter meets a preset condition, generating a control instruction set includes the following steps: when it is determined that the fusion collision parameter is a target detonation value, generating a control instruction set.

[0010] Optionally, the first collision parameter and the second collision parameter are processed using a fusion collision model in the collision prediction model to obtain a fusion collision parameter, including the following steps: when it is determined that the first collision parameter and the second collision parameter are both target parameter values, outputting the fusion collision parameter as a target detonation value.

[0011] Optionally, the road information and the collision acceleration are processed using the second collision model in the collision prediction model to obtain a second collision parameter, including the following steps: based on the road type, an acceleration threshold of the target vehicle is obtained, and the acceleration threshold is set to match the road type; when it is determined that the collision acceleration is greater than or equal to the acceleration threshold, the second collision parameter is output as the target parameter value.

[0012] Optionally, the obstacle information is processed using the first collision model in the collision prediction model to obtain a first collision parameter, including the following steps: the obstacle information is processed using the collision risk prediction model in the first collision model to obtain a collision risk value; based on the collision risk value, it is determined whether the target vehicle has a collision risk; when it is determined that the target vehicle has a collision risk and the obstacle type is a motor vehicle, the first collision parameter is output as the target parameter value.

[0013] Optionally, based on the collision risk value, determining whether the target vehicle has a collision risk includes the following steps: when it is determined that the collision risk value is less than a risk threshold, determining that the target vehicle has no collision risk; when it is determined that the collision risk value is greater than or equal to the risk threshold, determining that the target vehicle has a collision risk.

[0014] Optionally, when it is determined that the fused collision parameters meet the preset conditions, the method also includes the following steps: when it is determined that the fused collision parameters meet the preset conditions, obtaining collision data of the target vehicle, the collision data including at least obstacle data and vehicle driving data, the obstacle data including at least obstacle type, obstacle speed, obstacle acceleration and obstacle relative distance, the vehicle driving data including at least target vehicle speed, acceleration and steering wheel angle; storing the collision data in a database of the collision prediction model; and updating the collision prediction model based on the data in the database.

[0015] According to another aspect of an embodiment of the present invention, there is also provided an airbag control device, comprising: an acquisition module, the acquisition module is used to acquire driving information of a target vehicle, the driving information includes at least road information, obstacle information, and collision acceleration, wherein the road information includes at least road type, the road type includes at least smooth roads and bumpy roads, the obstacle information includes at least one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, obstacle types include special static obstacles, vulnerable traffic participants and motor vehicles, special static obstacles include at least sand piles, electric poles, trash cans and roadside trees, vulnerable traffic participants include at least pedestrians and non-motor vehicles; a collision prediction module, the collision prediction module is used to process the driving information using a collision prediction model to obtain fused collision parameters; a generation module, the generation module is used to generate a control instruction set when it is determined that the fused collision parameters meet preset conditions, and the control instruction set is used to control the detonation of the airbag.

[0016] Optionally, the acquisition module includes: a multi-source sensor perception module, which is used to acquire road information and obstacle information; the multi-source sensor perception module includes at least one of the following: a camera, a lidar, a millimeter-wave radar, an ultrasonic radar, a GPS and an IMU.

[0017] Optionally, the acquisition module also includes: an acceleration signal acquisition module, which is used to collect collision acceleration; the acceleration signal acquisition module includes at least one of the following: a front collision acceleration sensor, a side collision acceleration sensor and an onboard acceleration sensor, the front collision acceleration sensor and the side collision acceleration sensor are arranged on the outside of the target vehicle's body, and the onboard acceleration sensor is arranged on the inside of the target vehicle's body.

[0018] According to another aspect of the embodiments of the present invention, a vehicle is provided. The vehicle has an airbag, and the airbag is controlled by the above-mentioned airbag control method.

[0019] According to another aspect of the embodiments of the present invention, a computer program product is provided, including computer instructions, which implement the steps of the above-mentioned airbag control method when executed by a processor.

[0020] In an embodiment of the present invention, driving information of a target vehicle is obtained, and the driving information includes at least: road information, obstacle information, and collision acceleration, wherein the road information includes at least road type, and the road type includes at least smooth roads and bumpy roads, and the obstacle information includes at least one of the following: obstacle type, obstacle relative distance, obstacle relative speed, and obstacle relative acceleration, and the obstacle type includes special static obstacles, vulnerable traffic participants, and motor vehicles, and the special static obstacles include at least sand piles, electric poles, trash cans, and roadside trees, and the vulnerable traffic participants include at least pedestrians and non-motor vehicles; the driving information is processed using a collision prediction model to obtain fused collision parameters; when it is determined that the fused collision parameters meet preset conditions, a control instruction set is generated, and the control instruction set is used to control the detonation of the airbag. The airbag control method in this embodiment obtains driving information including road information, obstacle information, and collision acceleration, so that the finally obtained fused collision parameters take into account the influence of road surface and static roadblocks at the same time, thereby making the final airbag detonation control more accurate, improving the airbag control accuracy, and thus solving the technical problem of airbag misfire in related technologies, avoiding the problem that airbag misfire affects driver operation, endangers passenger safety, and reduces vehicle economy, preventing airbag misfire from injuring drivers and passengers, ensuring personal safety, reducing maintenance costs, and reducing user economic losses, thereby making the vehicle safer, more economical, and more practical. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0022] Figure 1is a hardware structure block diagram of an electronic device of a vehicle according to one embodiment of the present invention;

[0023] Figure 2 is a flow chart of an airbag control method according to one optional embodiment of the present invention;

[0024] Figure 3 is a structural block diagram of an airbag control device according to one embodiment of the present invention;

[0025] Figure 4 is a flow chart of an airbag control method according to one optional embodiment of the present invention;

[0026] Figure 5 is a flow chart of a collision risk prediction algorithm based on multi-source sensor perception according to one optional embodiment of the present invention;

[0027] Figure 6 is a flow chart of a collision risk assessment algorithm based on road surface recognition and an external acceleration sensor according to one optional embodiment of the present invention;

[0028] Figure 7 is a flow chart of a collision risk fusion algorithm based on multi-source sensor perception and external acceleration signals according to one optional embodiment of the present invention;

[0029] Figure 8 is a schematic diagram of the working principle of a collision risk prediction model based on multi-source sensor perception according to one of the optional embodiments of the present invention;

[0030] Fig. 9 is a structural block diagram of an airbag control device according to one optional embodiment of the present invention;

[0031] Fig.10 It is a schematic diagram of the structure of an airbag control electronic device according to one optional embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] According to one embodiment of the present invention, an embodiment of an airbag control method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] The method embodiment can be executed in an electronic device or similar computing device in a vehicle including a memory and a processor. For example, Figure 1 As shown, the electronic device of the vehicle may include one or more processors 102 (the processor may include but is not limited to a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microprocessor (MCU), a programmable logic device (FPGA), a neural network processor (NPU), a tensor processor (TPU), an artificial intelligence (AI) type processor, etc.) and a memory 104 for storing data. Optionally, the electronic device of the vehicle may also include a transmission device 106 for communication functions, an input and output device 108, and a display 110. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the electronic device of the vehicle. For example, the electronic device of the vehicle may include more or fewer components than those described in the above structure, or may have a configuration different from that described in the above structure.

[0036] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the airbag control method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above-mentioned airbag control method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0037] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0038] The display 110 may be, for example, a touch screen liquid crystal display (LCD). The liquid crystal display may enable a user to interact with a user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contact and / or gestures on a touch-sensitive surface, wherein the human-computer interaction functions here may optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music, and / or web browsing, etc. The executable instructions for executing the above human-computer interaction functions are configured / stored in a computer program product or a readable storage medium executable by one or more processors.

[0039] This embodiment provides a safety airbag control method running on the electronic device of the above vehicle. Figure 2 is a flow chart of an airbag control method according to one embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0040] Step S21, obtaining driving information of the target vehicle, the driving information at least includes: road information, obstacle information, collision acceleration, wherein the road information at least includes road type, the road type at least includes smooth road and bumpy road, the obstacle information at least includes one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, obstacle type includes special static obstacles, vulnerable traffic participants and motor vehicles, special static obstacles at least include sand piles, electric poles, trash cans and roadside trees, vulnerable traffic participants at least include pedestrians and non-motor vehicles;

[0041] Step S22, using the collision prediction model to process the driving information to obtain fused collision parameters;

[0042] Step S23, when it is determined that the fused collision parameter meets the preset condition, a control instruction set is generated, and the control instruction set is used to control the deployment of the safety airbag.

[0043] Through the above steps, the driving information of the target vehicle is obtained, and the driving information includes at least: road information, obstacle information, and collision acceleration, wherein the road information includes at least the road type, and the road type includes at least smooth roads and bumpy roads, and the obstacle information includes at least one of the following: obstacle type, obstacle relative distance, obstacle relative speed, and obstacle relative acceleration. The obstacle type includes special static obstacles, vulnerable traffic participants, and motor vehicles. Special static obstacles include at least sand piles, electric poles, trash cans, and roadside trees. Vulnerable traffic participants include at least pedestrians and non-motor vehicles; the driving information is processed using a collision prediction model to obtain fused collision parameters; when it is determined that the fused collision parameters meet preset conditions, a control instruction set is generated, and the control instruction set is used to control the detonation of the airbag. The airbag control method in this embodiment obtains driving information including road information, obstacle information, and collision acceleration, so that the finally obtained fused collision parameters take into account the influence of road surface and static roadblocks at the same time, thereby making the final airbag detonation control more accurate, improving the airbag control accuracy, and thus solving the technical problem of airbag misfire in related technologies, avoiding the problem that airbag misfire affects driver operation, endangers passenger safety, and reduces vehicle economy, preventing airbag misfire from injuring drivers and passengers, ensuring personal safety, reducing maintenance costs, and reducing user economic losses, thereby making the vehicle safer, more economical, and more practical.

[0044] The beneficial effects of the technical solution of the embodiment of the present application are as follows:

[0045] 1) In the embodiments of the present application, the road information at least includes the road type, and the road type at least includes smooth roads and bumpy roads, that is, the influence of the road type is fully considered in the process of calculating and obtaining the fused collision parameters. For different road conditions such as smooth roads and bumpy roads, the calculation process of the fused collision parameters can be different, so that the airbag detonation control conforms to the driving habits and driving characteristics of the vehicle on different roads. For example, when the vehicle is driving on a bumpy and rough road, such as a Belgian road or an off-road road, the risk of airbag misfire increases. At this time, the road type, obstacle information, and collision acceleration are simultaneously included in the airbag control judgment process, which can avoid the problem of airbag misfire caused by unstable vehicle driving on bumpy roads;

[0046] 2) In the embodiments of the present application, obstacle types include special static obstacles, vulnerable traffic participants and motor vehicles. Special static obstacles include at least sand piles, electric poles, trash cans and roadside trees. Vulnerable traffic participants include at least pedestrians and non-motor vehicles. That is, when performing airbag control, the impact of obstacle types is fully considered. Different obstacle types have different degrees of impact on passenger safety. For different obstacle types, the calculation method of fused collision parameters can be different to make the airbag control more in line with actual driving conditions. For example, when the obstacle is a static roadblock such as a sand pile, electric pole, trash can and roadside tree, the airbag can be controlled not to explode. When the obstacle is a motor vehicle, the airbag is controlled to explode.

[0047] 3) In the embodiments of the present application, the airbag detonation control is performed based on the road information, obstacle information, and collision acceleration at the same time. This can avoid the problem of accidental airbag explosion caused by the driver forcefully closing the door or engine hood when the vehicle is stationary in the prior art. That is, by comprehensively considering a variety of driving information, the problem of a single control process caused by a single consideration factor is avoided, and the control result is more accurate.

[0048] Optionally, in step S22, the driving information is processed using a collision prediction model to obtain fused collision parameters, including the following steps:

[0049] Step S221, using the first collision model in the collision prediction model to process the obstacle information to obtain a first collision parameter;

[0050] Step S222, using the second collision model in the collision prediction model to process the road information and the collision acceleration to obtain a second collision parameter;

[0051] Step S223: Process the first collision parameter and the second collision parameter using the fused collision model in the collision prediction model to obtain a fused collision parameter.

[0052] Through steps S221-S223, the first collision parameter is obtained by processing the obstacle information, which can be used to judge the influence of the current road on the airbag detonation control, and the second collision parameter is obtained by processing the road information and the collision acceleration, which can be used to judge the influence of the road information and the collision acceleration on the airbag detonation control. Based on the first collision parameter and the second collision parameter, the obtained fused collision parameter can comprehensively consider the influence of the obstacle information, the road information and the collision acceleration on the airbag detonation control, so that the final control result is more accurate. Steps S221-S223 make the calculation process of the fused collision parameter clearer and the information processing process clearer.

[0053] Optionally, in step S23, when it is determined that the fusion collision parameter meets the preset condition, a control instruction set is generated, including the following steps:

[0054] Step S231, when it is determined that the fused collision parameter is the target detonation value, a control instruction set is generated.

[0055] Through step S231, when the fused collision parameter is determined to be the target detonation value, the airbag is controlled to be detonated. The airbag control is convenient and fast. According to actual needs, the target detonation value can be multiple, or one, or any value within a predetermined value range. For example, a certain value range is set as a preset condition. When the fused collision parameter is any value within the value range, the fused collision parameter is determined to be the target detonation value, and the airbag is controlled to be detonated.

[0056] Optionally, in step S223, the first collision parameter and the second collision parameter are processed by using the fused collision model in the collision prediction model to obtain the fused collision parameter, including the following steps:

[0057] Step S2231: When it is determined that both the first collision parameter and the second collision parameter are target parameter values, the fused collision parameter is output as a target detonation value.

[0058] Through step S2231, when it is determined that the first collision parameter and the second collision parameter are both target parameter values, the fused collision parameter is output as the target detonation value, which can make the determination process of the fused collision parameter simpler. According to actual needs, the target parameter value can be the same parameter value, that is, when the first collision parameter and the second collision parameter are both a certain parameter value, the fused collision parameter is output as the target detonation value; the target parameter value can also include a first target parameter value and a second target parameter value, the first target parameter value corresponds to the first collision parameter, the second target parameter value corresponds to the second collision parameter, the first target parameter value and the second target parameter value are set differently, when the first collision parameter is the first target parameter value and the second collision parameter is the second target parameter value, the fused collision parameter is output as the target detonation value.

[0059] In an exemplary embodiment of the present application, the first collision parameter, the second collision parameter and the fused collision parameter all include two types: 0 and 1. When the first collision parameter and the second collision parameter are both 1, the fused collision parameter is output as 1 to control the airbag to be deployed. When any one of the first collision parameter and the second collision parameter is 0, the fused collision parameter is output as 0 and the airbag is not deployed. According to actual needs, it can also be set as follows: when any one of the first collision parameter and the second collision parameter is 1, the fused collision parameter is output as 1 to control the airbag to be deployed.

[0060] It should be understood that in addition to the above-mentioned embodiment of using two numerical values ​​of 0 and 1 for parameter setting, when setting specifically, the first collision parameter, the second collision parameter, and the fused collision parameter can also have more types of numerical values. For example, five or ten numerical results can be set for each parameter, and one or several numerical values ​​from the multiple numerical results can be selected as the target parameter value.

[0061] Optionally, in step S222, the road information and the collision acceleration are processed by using the second collision model in the collision prediction model to obtain the second collision parameter, including the following steps:

[0062] Step S2221, based on the road type, obtaining the acceleration threshold of the target vehicle, the acceleration threshold is set to match the road type;

[0063] Step S2222: when it is determined that the collision acceleration is greater than or equal to the acceleration threshold, output the second collision parameter as the target parameter value.

[0064] Through steps S2221-S2222, the acceleration threshold is determined according to the road type. For example, the acceleration threshold for a bumpy road is set greater than the acceleration threshold for a smooth road, so that the second collision parameter result is more consistent with the actual driving conditions and the airbag control is more accurate.

[0065] Optionally, in step S221, the obstacle information is processed using a first collision model in the collision prediction model to obtain a first collision parameter, including the following steps:

[0066] Step S2211, using the collision risk prediction model in the first collision model to process the obstacle information to obtain a collision risk value;

[0067] Step S2212, judging whether the target vehicle has a collision risk based on the collision risk value;

[0068] Step S2213: When it is determined that the target vehicle has a collision risk and the obstacle type is a motor vehicle, the first collision parameter is output as the target parameter value.

[0069] Through steps S2211 to S2213, the obstacle information is processed using the collision risk prediction model to obtain a collision risk value; based on the collision risk value, it is determined whether the target vehicle has a collision risk; when it is determined that the target vehicle has a collision risk and the obstacle type is a motor vehicle, the first collision parameter is output as the target parameter value. By combining the collision risk prediction and the specific obstacle type to output the first collision parameter, different airbag detonation controls can be implemented for different obstacles. In this embodiment, when the obstacle type is a motor vehicle, the first collision parameter is output as the target parameter value, which can ensure that the vehicle detonates the airbag in time when facing a highly dangerous obstacle such as a motor vehicle.

[0070] Optionally, in step S2212, judging whether the target vehicle has a collision risk based on the collision risk value includes the following steps:

[0071] Step S22121, when it is determined that the collision risk value is less than the risk threshold, it is determined that the target vehicle has no collision risk;

[0072] Step S22122: When it is determined that the collision risk value is greater than or equal to the risk threshold, it is determined that the target vehicle has a collision risk.

[0073] By comparing the collision risk value with the risk threshold through steps S22121-S22122, it is determined whether the target vehicle has a collision risk, which can make the judgment process simpler. The risk threshold can be a pre-set fixed value or a value calculated in time when the vehicle is driving.

[0074] Optionally, after step S23, when it is determined that the fusion collision parameter meets the preset condition, the method further includes the following steps:

[0075] Step S24, when it is determined that the fused collision parameter meets the preset conditions, the collision data of the target vehicle is obtained, the collision data at least includes obstacle data and self-vehicle driving data, the obstacle data at least includes obstacle type, obstacle speed, obstacle acceleration and obstacle relative distance, and the self-vehicle driving data at least includes speed, acceleration and steering wheel angle of the target vehicle;

[0076] Step S25, storing the collision data in a database of the collision prediction model;

[0077] Step S26: updating the collision prediction model based on the data in the database.

[0078] Through steps S24 to S26, when it is determined that the airbag is to be deployed, the collision data generated and collected during this control process is stored in the database of the collision prediction model, and the collision prediction model is updated, so that the data of the collision prediction model can be more diverse. Updating the model can make subsequent airbag control more accurate and meet the user's needs in various usage scenarios.

[0079] According to one embodiment of the present invention, a preferred embodiment of an airbag control method is also provided, such as Figure 4 As shown, the method comprises the following steps:

[0080] Step 1: Acquire the driving road and obstacle information through a multi-source sensor sensing method, and output a first collision parameter based on a collision risk prediction model sensed by the multi-source sensor;

[0081] Among them, multi-source sensors can be various sensors used in autonomous driving, including cameras, lidar, millimeter-wave radar, ultrasonic radar, GPS, and IMU, etc.; driving roads can be divided into smooth roads and bumpy roads according to control requirements; obstacles are objects that affect the driving of the vehicle, and are divided into special stationary obstacles, motor vehicles, pedestrians, and non-motor vehicles according to model requirements. Specifically, obstacle information includes type, driving speed, acceleration, and relative distance, etc. The above information is obtained through multi-source sensors.

[0082] Specifically, Figure 5 As shown in the figure, the collision risk prediction algorithm based on multi-source sensor perception is as follows: ① The obstacle type, relative distance, relative speed and relative acceleration information are taken as input; ② The collision risk prediction model based on multi-source sensors is used to output the collision risk value; ③ If the collision risk value is less than the risk threshold, it means that there is no collision risk between the obstacle and the vehicle; if the collision risk value is greater than or equal to the risk threshold, it means that there is a collision risk between the obstacle and the vehicle; ④ The obstacle type detected by the target is used as a verification condition. If the type is a special static obstacle or a vulnerable traffic participant, the first collision parameter is set to 0; if the type is other such as a motor vehicle, the first collision parameter is set to 1.

[0083] Through step 1, the obstacle information is input into the pre-trained collision risk prediction model based on multi-source sensor perception to obtain the first collision parameter. Since the model is trained with a limited data set, a collision data online update module is subsequently added to transmit the EDR collision data online to the cloud platform, expand the training data set, optimize the collision risk prediction model, and improve the accuracy and robustness of the prediction model, thereby improving the accuracy of the first collision parameter.

[0084] Specifically, in this embodiment, the working principle of the collision risk prediction model based on multi-source sensor perception is as follows: Figure 8As shown, the collision risk prediction model based on multi-source sensor perception specifically includes two parts: offline training of the collision risk prediction model based on multi-source sensor perception and using the trained model to predict the collision risk of online recognized data.

[0085] Among them, the offline training design steps specifically include: first designing the collision data set, then establishing a collision risk prediction model based on multi-source sensor perception through machine learning, and then conducting end-to-end model training.

[0086] The online prediction design steps include: first, obtaining obstacle, vehicle and road scene data in real time, then inputting it into the trained collision risk prediction model to output the collision risk value, then comparing it with the threshold to determine whether there is a collision risk, and finally uploading the data with collision risk to the cloud in real time, expanding the collision data set, and iteratively optimizing and improving the risk prediction model based on actual data to enhance the model's prediction capability.

[0087] Specifically, the collision dataset design process includes analyzing dataset requirements, dataset composition, data enhancement, dataset division and maintenance, etc., to avoid the decrease in model training accuracy due to non-standard datasets, significantly reduce model prediction capabilities, and increase training costs; at the same time, data enhancement can solve the problems of model overfitting and poor generalization ability, and improve convergence speed. The dataset composition mainly includes obstacle data, such as type, speed, acceleration and relative distance; vehicle driving data includes speed, acceleration and steering wheel angle, etc. Road type data is divided into smooth and bumpy types.

[0088] Construct a collision risk prediction model based on machine learning methods, including but not limited to deep neural networks, statistical machine learning, etc. During the model training process, the training speed can be accelerated through pre-training.

[0089] Step 2: using an external acceleration sensor to obtain a collision acceleration signal value, and outputting a second collision parameter based on a collision risk assessment algorithm based on road surface recognition and the external acceleration signal;

[0090] Among them, the external acceleration sensor can be a front impact acceleration sensor, a side impact acceleration sensor and an onboard acceleration sensor installed at different positions of the vehicle, which are used to output the acceleration values ​​of the X-axis and the Y-axis; road surface recognition refers to using a target detection algorithm to identify whether the road is a smooth road surface or a bumpy road surface, and calibrating different acceleration thresholds according to different road surface types. The acceleration threshold for a bumpy road surface is higher than the acceleration threshold for a smooth road surface.

[0091] like Figure 6As shown in FIG, the collision risk assessment algorithm based on road surface recognition and external acceleration sensors is as follows: ① The X-axis and Y-axis acceleration values ​​collected by the external acceleration sensors at various positions of the vehicle and the road type of the target detection are respectively used as input; ② If the road type is a bumpy road, calibrate the acceleration threshold suitable for the bumpy road; if the road type is a smooth road, calibrate the acceleration threshold suitable for the smooth road; wherein, the acceleration threshold suitable for the bumpy road is higher than the acceleration threshold suitable for the smooth road; ③ Determine whether the X-axis and Y-axis acceleration values ​​output by the main sensor in the external acceleration sensor meet the calibrated main acceleration threshold; ④ Determine whether the X-axis and Y-axis acceleration values ​​output by the auxiliary sensor meet the calibrated auxiliary acceleration threshold; ⑤ If both meet at the same time, set the second collision parameter to 1; otherwise, set the second collision parameter to 0.

[0092] Specifically, taking a bumpy road as an example, the collision risk assessment algorithm based on road surface recognition and external acceleration signals takes the detected road surface type, the X-axis and Y-axis acceleration values ​​output by the main sensor, and the Y-axis and Y-axis acceleration values ​​output by the auxiliary sensor as inputs; determines whether the X-axis and Y-axis acceleration values ​​output by the main sensor in the external acceleration sensor meet the calibrated bumpy road acceleration threshold, and then determines whether the X-axis and Y-axis acceleration values ​​output by the auxiliary sensor meet the calibrated bumpy road acceleration threshold. If both meet, the second collision parameter is output as 1, which means that the airbag ignition condition is met. The same applies to the algorithm for outputting the second collision parameter for a smooth road surface.

[0093] Step 3, based on the mutual verification of rationality between the first collision parameter and the second collision parameter, determining the fusion collision parameter;

[0094] Among them, the fused collision parameter is the final control quantity that triggers the airbag ignition. The fused collision parameter can be obtained by mutual verification of the first collision parameter and the second collision parameter. If the first collision parameter and the second collision parameter are both 1, it proves that the vehicle has collided and the degree of collision has reached the airbag ignition condition, and the airbag is detonated; if at least one of the first collision parameter and the second collision parameter is 0, it indicates that no collision has occurred or the collision degree has not reached the airbag ignition condition, and the airbag remains closed.

[0095] Specifically, Figure 7As shown in the figure, the collision risk fusion algorithm based on multi-source sensor perception and external acceleration signal is as follows: ① If the first collision parameter is 1 and the second collision parameter is also 1, the fused collision parameter is determined to be 1; ② If at least one of the first collision parameter and the second collision parameter is 0, the fused collision parameter is determined to be 0. The advantage of this fusion algorithm is that it adds a safety mechanism (using multi-source sensors to predict collision risks), uses two methods to judge the airbag ignition conditions, and fuses to determine whether the airbag is detonated, which can improve the airbag control accuracy, reduce the false explosion rate, protect the personal safety of drivers and passengers, and reduce the maintenance cost of the vehicle.

[0096] Step 4: The collision parameters are integrated as airbag ignition condition parameters to control the safe explosion of the airbag.

[0097] Specifically, the fused collision parameter is used as the input of the airbag ignition. If the fused collision parameter is 1, the ignition circuit is driven and the airbag is ignited; if the fused collision parameter is 0, the airbag is not ignited.

[0098] The airbag control method in this embodiment obtains the information of the driving road and obstacles through multi-source sensor perception, and outputs the first collision parameter based on the collision risk prediction model perceived by the multi-source sensor; obtains the collision acceleration signal value through the external acceleration sensor, and outputs the second collision parameter based on the collision risk assessment algorithm of the road surface recognition and the external acceleration signal; outputs the fused collision parameter based on the mutual verification of the rationality of the first collision parameter and the second collision parameter; at the same time, the EDR collision data is transmitted back to the cloud platform to train the collision risk prediction model to improve the robustness of the first collision parameter under limited perception; finally, the fused collision parameter controls the safe detonation of the airbag. The fusion algorithm model can solve the problem of the airbag being easily triggered to explode by mistake when the traditional single external acceleration sensor judges the second collision parameter. Specifically, through multi-source sensor perception and judgment of obstacle types, the vehicle can avoid the risk of misfiring airbags due to the second collision parameter being met when colliding with special static obstacles such as sand piles, telephone poles and roadside trees, as well as vulnerable road participants such as pedestrians and non-motor vehicles. It can also avoid the risk of misfiring airbags due to the large self-vibration of the vehicle when opening and closing doors, engine hood and trunk lid, which may lead to the second collision parameter being met. Further, through road recognition and classification and calibration of acceleration thresholds, it can avoid the risk of misfiring airbags due to the second collision parameter being easily met when driving on bumpy roads such as Belgium.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0100] In this embodiment, an airbag control device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0101] Figure 3 is a structural block diagram of an airbag control device according to one embodiment of the present invention. Figure 3 As shown, the device includes: an acquisition module 30, the acquisition module 30 is used to acquire the driving information of the target vehicle, the driving information includes at least: road information, obstacle information, collision acceleration, wherein the road information includes at least the road type, the road type includes at least smooth roads and bumpy roads, the obstacle information includes at least one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, obstacle types include special static obstacles, vulnerable traffic participants and motor vehicles, special static obstacles include at least sand piles, telephone poles, trash cans and roadside trees, vulnerable traffic participants include at least pedestrians and non-motor vehicles; a collision prediction module 32, the collision prediction module 32 is used to process the driving information using a collision prediction model to obtain fused collision parameters; a generation module 34, the generation module 34 is used to generate a control instruction set when it is determined that the fused collision parameters meet the preset conditions, and the control instruction set is used to control the detonation of the airbag.

[0102] The driving information of the target vehicle is obtained through the above-mentioned device, and the driving information includes at least: road information, obstacle information, and collision acceleration, wherein the road information includes at least road type, and the road type includes at least smooth road and bumpy road, and the obstacle information includes at least one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, obstacle type includes special static obstacles, vulnerable traffic participants and motor vehicles, special static obstacles include at least sand piles, electric poles, trash cans and roadside trees, and vulnerable traffic participants include at least pedestrians and non-motor vehicles; the driving information is processed by using a collision prediction model to obtain fused collision parameters; when it is determined that the fused collision parameters meet the preset conditions, a control instruction set is generated, and the control instruction set is used to control the detonation of the airbag. The airbag control method in this embodiment obtains driving information including road information, obstacle information, and collision acceleration, so that the finally obtained fused collision parameters take into account the influence of road surface and static roadblocks at the same time, thereby making the final airbag detonation control more accurate, improving the airbag control accuracy, and thus solving the technical problem of airbag misfire in related technologies, avoiding the problem that airbag misfire affects driver operation, endangers passenger safety, and reduces vehicle economy, preventing airbag misfire from injuring drivers and passengers, ensuring personal safety, reducing maintenance costs, and reducing user economic losses, thereby making the vehicle safer, more economical, and more practical.

[0103] Optionally, the acquisition module 30 includes a multi-source sensor perception module 301, which is used to acquire road information and obstacle information; the multi-source sensor perception module includes at least one of the following: camera, laser radar, millimeter wave radar, ultrasonic radar, GPS (Global Positioning System) and IMU (Inertial Measurement Unit). By setting up a multi-source sensor perception module, a variety of vehicle data can be collected, thereby making the recognition of road information and obstacle information more accurate, and making the airbag control result more accurate.

[0104] Optionally, the acquisition module 30 further includes an acceleration signal acquisition module 302, which is used to acquire collision acceleration; the acceleration signal acquisition module includes at least one of the following: a front collision acceleration sensor, a side collision acceleration sensor, and an onboard acceleration sensor, the front collision acceleration sensor and the side collision acceleration sensor are arranged outside the body of the target vehicle, and the onboard acceleration sensor is arranged inside the body of the target vehicle. The acceleration signal acquisition module can acquire external collision data and internal acceleration data of the vehicle, so that the vehicle status monitoring result is more accurate, thereby ensuring the accuracy of the airbag control result.

[0105] According to another aspect of the present invention, a preferred embodiment of an airbag control device is provided. Fig. 9 As shown, the device includes a multi-source sensor perception module, an external acceleration signal acquisition module, a collision risk assessment module, an online update module and an airbag ignition module. Among them, the multi-source sensor perception module is used to obtain the information of the driving road and obstacle targets, such as road type, obstacle type, speed, acceleration, relative distance, etc., as input for calculating the first collision parameter. The external acceleration signal acquisition module is used to obtain the acceleration signal as input for calculating the second collision parameter; the collision risk assessment module includes a collision risk prediction model based on multi-source sensor perception, a collision risk assessment algorithm based on road recognition and external acceleration signals, and a collision risk fusion algorithm based on multi-source sensors and external acceleration signals, and outputs fused collision parameters; the online update module is used to transmit the EDR collision data back to the cloud platform, train the collision risk prediction model based on multi-source sensor perception, and improve the model control accuracy; the airbag ignition module uses the fused collision parameters as input to control the detonation of the airbag.

[0106] Among them, EDR collision data refers to the collision-related data recorded by the event data recorder (EDR) installed on the vehicle when a collision occurs. These data include information such as the time of the collision, speed, acceleration, braking conditions, and airbag deployment.

[0107] Specifically, the specific uses of the multi-source sensor perception module include: ① Establishing a road database and an obstacle database, dividing the road types into smooth roads and bumpy roads; the obstacle types are divided into special static obstacles, vulnerable traffic participants and motor vehicles. Specifically, special static obstacles include green bushes such as sand piles, electric poles, trash cans and roadside trees; vulnerable traffic participants include pedestrians and bicycles; motor vehicles include cars, motorcycles and tricycles. ② Using multi-source sensor fusion algorithms such as cameras, millimeter wave radars, lidars, ultrasonic radars, GPS and IMU to obtain the road and obstacle target driving information in front of the vehicle. ③ Using target detection algorithms to detect road types and obstacle types, target detection algorithms such as the convolutional neural network YOLO series; ④ Output road type, obstacle type, relative distance, relative speed and relative acceleration information.

[0108] Specifically, the external acceleration signal acquisition module includes a front impact acceleration sensor, a side impact acceleration sensor and an onboard acceleration sensor installed at different positions, and is used to output acceleration values ​​of the X-axis and the Y-axis.

[0109] Specifically, the collision risk assessment module includes a collision risk prediction algorithm based on multi-source sensor perception, a collision risk assessment algorithm based on road surface recognition and external acceleration signals, and a collision risk fusion algorithm based on multi-source sensor perception and external acceleration signals.

[0110] Specifically, the specific uses of the online update module include: ① obtaining vehicle dynamics data recorded by EDR before, during and after the collision, such as vehicle speed, acceleration, steering wheel angle and other information; ② obtaining the relative distance, relative speed and relative acceleration information of the two vehicles recorded by multi-source sensors; ③ inputting the above information into the cloud platform to expand the collision risk prediction algorithm database; ④ real-time training of the algorithm to output more accurate first collision parameters.

[0111] Specifically, the specific uses of the airbag ignition module include: ① using the fused collision parameter as the input for airbag ignition; ② if the fused collision parameter is 1, driving the ignition circuit and the airbag is ignited; if the fused collision parameter is 0, the airbag is not ignited.

[0112] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0113] According to another aspect of the embodiment of the present invention, there is also provided an airbag control electronic device, such as Fig.10 As shown, the device includes a sensor, a processor, a memory, a communication interface and a communication bus. The sensor is used to obtain external information; the memory is used to store program data; the processor is used to execute the program data stored in the memory; and the information exchange between the sensor, processor, memory and communication interface is completed through the communication bus.

[0114] According to another aspect of the embodiments of the present invention, a vehicle is provided. The vehicle has an airbag, and the airbag is controlled by the airbag control method in the above embodiment.

[0115] By applying the airbag control method in the above embodiment to control the vehicle, the vehicle can have the following beneficial effects:

[0116] 1) The airbag control method in this embodiment proposes a collision risk prediction model based on multi-source sensor perception, and performs collision risk prediction through multi-source sensor perception and target detection algorithm, thereby solving the risk of airbag misfire caused by vehicle self-vibration; and the online update module transmits collision data in real time to improve the accuracy of collision risk prediction;

[0117] 2) The airbag control method in this embodiment proposes a collision risk assessment algorithm based on road recognition and external acceleration. The collision risk assessment is performed through road recognition and external acceleration signals, which solves the problem of airbag misfire on bumpy roads such as Belgium.

[0118] 3) The airbag control method in this embodiment proposes a collision risk fusion algorithm based on multi-source sensor perception and external acceleration signals to improve the airbag control accuracy and greatly reduce the harm caused by false explosions.

[0119] According to another aspect of the embodiments of the present invention, a computer program product is provided, including computer instructions, which implement the steps of the airbag control method in the above embodiment when the computer instructions are executed by a processor.

[0120] Optionally, in this embodiment, the computer program product may be configured to store a computer program for performing the following steps:

[0121] Step S1, obtaining driving information of the target vehicle, the driving information at least includes: road information, obstacle information, collision acceleration, wherein the road information at least includes road type, the road type at least includes smooth road and bumpy road, the obstacle information at least includes one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, obstacle type includes special static obstacles, vulnerable traffic participants and motor vehicles, special static obstacles at least include sand piles, electric poles, trash cans and roadside trees, vulnerable traffic participants at least include pedestrians and non-motor vehicles;

[0122] Step S2, using a collision prediction model to process the driving information to obtain fused collision parameters;

[0123] Step S3, when it is determined that the fused collision parameter meets the preset conditions, a control instruction set is generated, and the control instruction set is used to control the deployment of the safety airbag.

[0124] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0125] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0126] Step S1, obtaining driving information of the target vehicle, the driving information at least includes: road information, obstacle information, collision acceleration, wherein the road information at least includes road type, the road type at least includes smooth road and bumpy road, the obstacle information at least includes one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, obstacle type includes special static obstacles, vulnerable traffic participants and motor vehicles, special static obstacles at least include sand piles, electric poles, trash cans and roadside trees, vulnerable traffic participants at least include pedestrians and non-motor vehicles;

[0127] Step S2, using a collision prediction model to process the driving information to obtain fused collision parameters;

[0128] Step S3, when it is determined that the fused collision parameter meets the preset conditions, a control instruction set is generated, and the control instruction set is used to control the deployment of the safety airbag.

[0129] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0130] An embodiment of the present invention further provides a processor, which is configured to run a computer program to execute the steps in any of the above method embodiments.

[0131] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0132] Step S1, obtaining driving information of the target vehicle, the driving information at least includes: road information, obstacle information, collision acceleration, wherein the road information at least includes road type, the road type at least includes smooth road and bumpy road, the obstacle information at least includes one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, obstacle type includes special static obstacles, vulnerable traffic participants and motor vehicles, special static obstacles at least include sand piles, electric poles, trash cans and roadside trees, vulnerable traffic participants at least include pedestrians and non-motor vehicles;

[0133] Step S2, using a collision prediction model to process the driving information to obtain fused collision parameters;

[0134] Step S3, when it is determined that the fused collision parameter meets the preset conditions, a control instruction set is generated, and the control instruction set is used to control the deployment of the safety airbag.

[0135] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0136] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0138] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0140] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A safety airbag control method, characterized in that: The method comprises the following steps: Acquire driving information of the target vehicle, the driving information at least including: road information, obstacle information, and collision acceleration, wherein the road information at least includes road type, the road type at least includes smooth roads and bumpy roads, the obstacle information at least includes one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, the obstacle type includes special static obstacles, vulnerable traffic participants, and motor vehicles, the special static obstacles at least include sand piles, electric poles, trash cans, and roadside trees, and the vulnerable traffic participants at least include pedestrians and non-motor vehicles; Processing the driving information using a collision prediction model to obtain fused collision parameters; When it is determined that the fused collision parameter meets a preset condition, a control instruction set is generated, wherein the control instruction set is used to control the detonation of the safety airbag; In the case where the fusion collision parameter is determined to be a target detonation value, generating the control instruction set; The method of processing the driving information using a collision prediction model to obtain fused collision parameters includes the following steps: The obstacle information is processed using a first collision model in the collision prediction model to obtain a first collision parameter; the road information and the collision acceleration are processed using a second collision model in the collision prediction model to obtain a second collision parameter; the first collision parameter and the second collision parameter are processed using a fusion collision model in the collision prediction model to obtain the fusion collision parameter; When it is determined that the first collision parameter and the second collision parameter are both target parameter values, outputting the fused collision parameter as the target detonation value; Processing the obstacle information using the collision risk prediction model in the first collision model to obtain a collision risk value; Based on the collision risk value, determining whether the target vehicle has a collision risk; When it is determined that the target vehicle has the collision risk and the obstacle type is the motor vehicle, outputting the first collision parameter as the target parameter value; Based on the road type, acquiring an acceleration threshold of the target vehicle, wherein the acceleration threshold is set to match the road type; When it is determined that the collision acceleration is greater than or equal to the acceleration threshold, the second collision parameter is output as the target parameter value.

2. The method according to claim 1, characterized in that Based on the collision risk value, determining whether the target vehicle has a collision risk comprises the following steps: In the case where it is determined that the collision risk value is less than the risk threshold, determining that the target vehicle has no collision risk; When it is determined that the collision risk value is greater than or equal to a risk threshold, it is determined that the target vehicle has a collision risk.

3. The method according to claim 1, characterized in that When it is determined that the fusion collision parameter meets the preset condition, the method further includes the following steps: When it is determined that the fused collision parameter meets the preset condition, the collision data of the target vehicle is obtained, the collision data at least including obstacle data and self-vehicle driving data, the obstacle data at least including obstacle type, obstacle speed, obstacle acceleration and obstacle relative distance, and the self-vehicle driving data at least including speed, acceleration and steering wheel angle of the target vehicle; storing the collision data in a database of the collision prediction model; The collision prediction model is updated based on the data in the database.

4. An airbag control device, characterized in that: The airbag control device is controlled by the airbag control method according to any one of claims 1 to 3, and the airbag control device comprises: An acquisition module, the acquisition module is used to acquire driving information of the target vehicle, the driving information at least includes: road information, obstacle information, collision acceleration, wherein the road information at least includes road type, the road type at least includes smooth road and bumpy road, the obstacle information at least includes one of the following: obstacle type, obstacle relative distance, obstacle relative speed, obstacle relative acceleration, the obstacle type includes special static obstacles, vulnerable traffic participants and motor vehicles, the special static obstacles at least include sand piles, electric poles, garbage cans and roadside trees, and the vulnerable traffic participants at least include pedestrians and non-motor vehicles; A collision prediction module, the collision prediction module is used to process the driving information using a collision prediction model to obtain a fused collision parameter; A generation module is used to generate a control instruction set when it is determined that the fused collision parameter meets a preset condition, and the control instruction set is used to control the detonation of the safety airbag.

5. The control device according to claim 4, characterized in that: The acquisition module comprises: A multi-source sensor perception module, wherein the multi-source sensor perception module is used to obtain the road information and the obstacle information; The multi-source sensor perception module includes at least one of the following: a camera, a laser radar, a millimeter-wave radar, an ultrasonic radar, a GPS, and an IMU.

6. The control device according to claim 4, characterized in that: The acquisition module also includes: An acceleration signal acquisition module, wherein the acceleration signal acquisition module is used to acquire the collision acceleration; The acceleration signal acquisition module includes at least one of the following: a front collision acceleration sensor, a side collision acceleration sensor and an onboard acceleration sensor, the front collision acceleration sensor and the side collision acceleration sensor are arranged outside the body of the target vehicle, and the onboard acceleration sensor is arranged inside the body of the target vehicle.

7. A vehicle, characterized in that: The vehicle has an airbag, and the airbag is controlled by the airbag control method according to any one of claims 1 to 3.

8. A computer program product comprising computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the airbag control method according to any one of claims 1 to 3 are implemented.

Images