Safety-identification vehicle control method and system based on multi-data-fusion sensing
Patent Information
- Application Number
- PCT/CN2025/148249
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-04-17
- Filing Date
- 2025-12-31
- Publication Date
- 2026-10-22
Smart Images
Figure CN2025148249_22102026_PF_FP_ABST
Abstract
Description
A Safety Identification Vehicle Control Method and System Based on Multi-Data Fusion Perception
[0001] Cross-references to related applications
[0002] This application claims priority to Chinese Patent Application No. 202510485616.0, filed on April 17, 2025, entitled "Safety Identification Vehicle Control Method and System Based on Multi-Data Fusion Perception", the entire contents of which are incorporated herein by reference and constitute a part of this invention for all purposes. Technical Field
[0003] This application relates to the fields of automation control and traffic safety technology, and to a method and system for safety identification and vehicle control based on multi-data fusion perception. Background Technology
[0004] The statements in this section are merely background information related to this application and do not necessarily constitute prior art.
[0005] With the increasing number of cars in people's lives, accidents involving pedestrians or drivers suffering from road rage are also on the rise. Therefore, effectively protecting drivers when encountering road rage incidents has become a critical traffic safety challenge that needs to be addressed.
[0006] Existing methods for identifying whether other drivers are experiencing road rage include, for example, a patent with publication number CN109498041A that discloses a "method for identifying driver road rage based on EEG and pulse information." This method collects and analyzes the driver's EEG and pulse signals to assist in identifying whether the driver may be experiencing road rage. It uses biosignals to analyze the driver, but it is limited in accurately identifying whether other drivers have a tendency to experience road rage. This is because it is impossible to accurately obtain the biosignals of other drivers, leading to inaccurate results in identifying whether other drivers are experiencing road rage. In addition, this method suffers from the problem of relying on a single set of data and conditions for judgment. Using only a single condition for identification can lead to an inaccurate assessment of potential dangers during driving, thus threatening the driver. Summary of the Invention
[0007] To address the aforementioned issues, this application proposes a safety identification vehicle control method and system based on multi-data fusion perception. By monitoring and identifying vehicle collision perception, seat pressure perception, door opening and closing triggering status, and door position, the system determines whether the driver will be harmed by pedestrians with road rage or other drivers, thereby executing safety control strategies to prevent the driver from being harmed.
[0008] Firstly, this application provides a safety identification vehicle control method based on multi-data fusion perception;
[0009] Safety identification vehicle control methods based on multi-data fusion perception include:
[0010] Set preset conditions for activating the vehicle safety protection mechanism;
[0011] The system acquires various sensor data from the vehicle, uses this data to identify the vehicle's safety status, and determines whether the identification results meet preset conditions. When all preset conditions are met, the vehicle safety protection mechanism is activated, and preset protection actions are implemented to protect the occupants.
[0012] The preset conditions include a first preset condition, a second preset condition, a third preset condition, a fourth preset condition, and a fifth preset condition. The process of determining whether the fifth preset condition is met is as follows: acquire vehicle location information and external environment information, input the vehicle location information and external environment information into a probability-based road rage risk assessment model, identify and analyze the behavior of people outside the vehicle, determine whether there is harmful behavior based on the facial expressions and body movements of the identified people outside the vehicle, and if the output probability meets the probability threshold, it is determined that there is harmful behavior, and at this time the fifth preset condition is met.
[0013] In some implementations, various vehicle sensing data include vehicle driving data, left front door opening angle, left front seat pressure data, left front door opening / closing trigger signal, vehicle location information, and surrounding environment information.
[0014] In some implementations, vehicle collision information is obtained based on the status of the vehicle collision sensor to determine whether a collision has occurred, and vehicle driving data, including vehicle speed, distance to other vehicles, and road condition information, is obtained. The vehicle speed, distance to other vehicles, and road condition information are analyzed by a neural network. Based on the current vehicle speed, the distance to the vehicle in front or the obstacle, and the friction coefficient of the road, the probability of a future vehicle collision is predicted. If the vehicle identification result is that no collision has occurred, then the first preset condition is met.
[0015] In some implementations, the opening angle of the left front door is obtained by the state of the left front door opening sensor, and it is determined whether the left front door is in a closed state based on the opening angle of the left front door. If the left front door is in a closed state, then the second preset condition is met.
[0016] In some implementations, the driver's position information is obtained by the state of the left front seat pressure sensor to determine whether there is a driver in the left front seat. If there is a driver in the left front seat, the third preset condition is met. The trigger source of the left front door opening command is obtained based on the trigger source state of the left front door switch. The trigger signal of the door switch is analyzed by a signal analysis algorithm to determine whether the left front door opening command is triggered by an external door button. If the left front door opening command is triggered by an external door button, the fourth preset condition is met.
[0017] In some implementations, the judgment results of five preset conditions are input into the decision tree node, and a decision is made through a pre-built decision tree model. When all preset conditions are met, the left front door of the vehicle is prevented from opening.
[0018] Secondly, this application provides a safety identification vehicle control system based on multi-data fusion perception;
[0019] A safety identification vehicle control system based on multi-data fusion perception includes:
[0020] The initialization module is used to set the preset conditions for activating the vehicle safety protection mechanism;
[0021] The control module is used to acquire various sensor data of the vehicle, use the various sensor data to identify the vehicle safety status, determine whether the identification result of the vehicle safety status meets the preset conditions, and when all preset conditions are met, the vehicle safety protection mechanism is activated and preset protection actions are implemented to protect the driver and passengers.
[0022] The preset conditions include a first preset condition, a second preset condition, a third preset condition, a fourth preset condition, and a fifth preset condition. The process of determining whether the fifth preset condition is met is as follows: acquire vehicle location information and external environment information, input the vehicle location information and external environment information into a probability-based road rage risk assessment model, identify and analyze the behavior of people outside the vehicle, determine whether there is harmful behavior based on the facial expressions and body movements of the identified people outside the vehicle, and if the output probability meets the probability threshold, it is determined that there is harmful behavior, and at this time the fifth preset condition is met.
[0023] Thirdly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned safety identification vehicle control method based on multi-data fusion perception.
[0024] Fourthly, this application provides a non-transitory computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the aforementioned safety identification vehicle control method based on multi-data fusion perception.
[0025] Fifthly, this application provides an electronic device, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the aforementioned safety identification vehicle control method based on multi-data fusion perception.
[0026] Compared with the prior art, the beneficial effects of this disclosure are as follows:
[0027] The safety identification vehicle control method based on multi-data fusion perception disclosed herein can more comprehensively and accurately determine whether other vehicle drivers have a tendency of "road rage" through the fusion of multiple perception data and multi-condition judgment logic. This allows for accurate identification of whether a driver is facing danger, providing early warning and judgment before the actual occurrence of danger, and activating safety protection mechanisms in advance. It improves the accuracy of judging whether other vehicle drivers have a tendency of "road rage" and fills the gap in protecting drivers from pedestrian injuries caused by "road rage," thereby improving driver safety during driving.
[0028] This disclosed method for safe vehicle control based on multi-data fusion perception sets five preset conditions for judgment and identification, reducing judgment and identification errors and improving the accuracy and effectiveness of identifying whether other vehicle drivers have a tendency towards road rage, thereby improving driving safety. The fifth preset condition is not limited to whether a collision has already occurred; different levels can be set based on the prediction results. For example, if the predicted probability of a collision exceeds 50% within the next 3 seconds, it is considered a special "pre-collision" state, judged using machine learning algorithms (such as neural network algorithms), providing a more comprehensive basis for driver protection decisions. It utilizes a large amount of vehicle driving data for identification and judgment, enabling it to predict the possibility of a vehicle collision in advance. For example, by collecting data from various situations such as normal driving, emergency braking, and minor collisions, and learning from the data through neural networks, it can predict the probability of a vehicle collision within the next few seconds based on factors such as the current vehicle speed, the distance to the vehicle in front or an obstacle, and the road friction coefficient, thus improving the accuracy of identifying road rage. Attached Figure Description
[0029] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an undue limitation of this application.
[0030] Figure 1 is a flowchart of a safety identification vehicle control method based on multi-data fusion perception according to an embodiment of this application;
[0031] Figure 2 is a schematic diagram of the system structure of the safety identification vehicle control method based on multi-data fusion perception according to an embodiment of this application. Detailed Implementation
[0032] The present application will be further described below with reference to the accompanying drawings and embodiments.
[0033] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of this application. Unless otherwise specified, 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 application pertains.
[0034] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.
[0035] Example 1
[0036] This application presents a safety identification vehicle control method based on multi-data fusion perception, providing an intelligent method and system for protecting drivers and addressing traffic accidents caused by road rage. The steps include:
[0037] Step 1: Set the preset conditions for activating the vehicle safety protection mechanism;
[0038] Step 2: Acquire various vehicle perception data, use these data to identify the vehicle's safety status, and determine whether the identification results meet preset conditions. When all preset conditions are met, the vehicle safety protection mechanism is activated, and preset protection actions are implemented to protect the occupants.
[0039] The preset conditions include a first preset condition, a second preset condition, a third preset condition, a fourth preset condition, and a fifth preset condition. The process of determining whether the fifth preset condition is met is as follows: acquire vehicle location information and external environment information, input the vehicle location information and external environment information into a probability-based road rage risk assessment model, identify and analyze the behavior of people outside the vehicle, determine whether there is harmful behavior based on the facial expressions and body movements of the identified people outside the vehicle, and if the output probability meets the probability threshold, it is determined that there is harmful behavior, and at this time the fifth preset condition is met.
[0040] As one embodiment, the safety identification vehicle control method based on multi-data fusion perception of this application achieves intelligent judgment based on multiple vehicle perception data, including vehicle driving data, left front door opening angle, left front seat pressure data, left front door switch trigger signal, vehicle position information, and surrounding environment information. Preset conditions are set for activating the vehicle safety protection mechanism, including a first, second, third, fourth, and fifth preset conditions. When each of the five preset conditions is met, the left front door control module controls the left front door to be closed, thereby protecting the driver's safety. The specific implementation process is as follows:
[0041] Step 101: The vehicle collision sensor acquires vehicle collision information and determines whether the vehicle meets the preset conditions for collision information. If a collision occurs, a positive feedback is given to the left front door control module. The left front door control module is used to control whether the left front door is opened and execute control commands.
[0042] Based on the status of vehicle collision sensors, vehicle collision information is acquired to determine whether a collision has occurred. The preset conditions for vehicle collision information are not limited to whether a collision has already occurred; different levels can be set based on the prediction results. For example, if the predicted probability of a collision exceeds 50% within the next 3 seconds, it is considered a special "pre-collision" state. This state can be determined using machine learning algorithms (such as neural network algorithms) to provide a more comprehensive basis for driver protection decisions. The determination process includes:
[0043] A neural network model is trained using a large amount of vehicle driving data (including vehicle speed, distance, road conditions, etc.) to predict the likelihood of vehicle collisions in advance. For example, data from various scenarios such as normal driving, emergency braking, and minor collisions are collected and divided into training and testing sets. The neural network then learns from the data to train the model.
[0044] As one embodiment, based on the current vehicle speed, the distance to the vehicle in front or the obstacle, and the road friction coefficient, the current vehicle speed, the distance to the vehicle in front or the obstacle, and the road friction coefficient are input into a trained neural network model, and the prediction result is output to predict the probability of the vehicle colliding in the next few seconds; if it is determined that the vehicle has not collided or there is no possibility of collision in the future, then the first preset condition is met.
[0045] Step 102: The left front door opening sensor acquires the opening status of the left front door and determines whether the left front door meets the preset conditions for door opening. If the left front door is closed, a positive feedback is given to the left front door control module.
[0046] Specifically, based on the state of the left front door opening sensor, the opening angle of the left front door is obtained, and it is determined whether the left front door is in a closed state. If the left front door is in a closed state, the second preset condition is met.
[0047] Step 103: The left front seat pressure sensor obtains the pressure information on the left front seat and determines whether there is a driver on the left front seat. If the pressure value detected by the left front seat pressure sensor exceeds the threshold, it is determined that there is a driver on the left front seat, and a positive feedback is given to the left front door control module.
[0048] Specifically, based on the state of the left front seat pressure sensor, the driver's position information is obtained to determine whether there is a driver in the left front seat. If there is a driver in the left front seat, the third preset condition is met.
[0049] Step 104: The left front door switch module determines the trigger source of the door opening command and determines whether the opening command is triggered by an external button. If the opening command is triggered by an external button, then a positive feedback is given to the left front door control module.
[0050] Specifically, based on the trigger source state of the left front door switch, the trigger source of the left front door opening command is obtained. Using existing signal analysis algorithms, the trigger signal of the door switch is analyzed to determine whether the left front door opening command is triggered by the door external button. The signal analysis algorithm involves collecting voltage data and timestamps from the door switch circuit, filtering the collected voltage data and timestamps to remove interference. If the analyzed voltage is within the threshold range of the left front door external button voltage and the voltage change slope matches the set slope range of the left front door external button voltage, it is determined that the left front door opening command is triggered by the left front door external button. If the left front door opening command is triggered by the door external button, then the fourth preset condition is met.
[0051] Step 105: The vehicle positioning and surrounding information processing module determines whether the vehicle is in a road rage location and whether the surrounding people are in a "road rage" state. If it is determined that the vehicle is in a "road rage" location and the surrounding people are in a "road rage" state, a positive feedback message is sent to the left front door control module.
[0052] Specifically, the vehicle's location information is obtained through GPS, and the external environment information is obtained through surround-view cameras. The vehicle's location information and the external environment information are input into a probability-based road rage risk assessment model. For example, in traffic-congested sections, highway entrances and exits, and other locations prone to road rage, the probability-based road rage risk assessment model is used to analyze the behavior of people outside the vehicle. The probability-based road rage risk assessment model can be a convolutional neural network (CNN) model in deep learning to recognize the facial expressions and body movements of people outside the vehicle. If angry facial expressions (such as frowning, glaring, gritting teeth, etc.) or aggressive body movements (such as waving arms, kicking vehicles, etc.) are recognized, it is determined that there may be road rage, and the assessment weight of road rage risk is increased. If the assessment weight of the road rage risk assessment model exceeds 80%, the fifth preset condition is met.
[0053] Step 106: The left front door control module obtains whether the above information meets all the preset conditions. If all the feedback received is positive, the left front door control module refuses to execute the door opening command and keeps the door closed. If at least one of the feedback received is negative, the left front door control module receives the door opening command and can open the left front door.
[0054] Specifically, the left front door control module inputs the preset conditions into the decision tree node. Through the pre-built decision tree model, the decision tree algorithm is used to make a decision. That is, if all the preset conditions are met, the left front door of the vehicle cannot be opened, in order to protect the driver from being harmed by people with "road rage".
[0055] Example 2
[0056] One embodiment of this application provides a safety identification vehicle control system based on multi-data fusion perception, including:
[0057] The initialization module is used to set the preset conditions for activating the vehicle safety protection mechanism;
[0058] The control module is used to acquire various sensor data of the vehicle, use the various sensor data to identify the vehicle safety status, determine whether the identification result of the vehicle safety status meets the preset conditions, and when all preset conditions are met, the vehicle safety protection mechanism is activated and preset protection actions are implemented to protect the driver and passengers.
[0059] The preset conditions include a first preset condition, a second preset condition, a third preset condition, a fourth preset condition, and a fifth preset condition. The process of determining whether the fifth preset condition is met is as follows: acquire vehicle location information and external environment information, input the vehicle location information and external environment information into a probability-based road rage risk assessment model, identify and analyze the behavior of people outside the vehicle, determine whether there is harmful behavior based on the facial expressions and body movements of the identified people outside the vehicle, and if the output probability meets the probability threshold, it is determined that there is harmful behavior, and at this time the fifth preset condition is met.
[0060] As one embodiment, as shown in Figure 2, the control module includes a vehicle collision sensor module 201, a left front door opening sensor module 202, a left front seat pressure sensor module 203, a left front door switch module 204, a vehicle positioning and surrounding information processing module 205, and a left front door control module 206. The vehicle collision sensor module 201 includes a vehicle collision sensor, the left front door opening sensor module 202 includes a left front door opening sensor, the left front seat pressure sensor module 203 includes a left front seat pressure sensor, the left front door switch module 204 includes a left front door switch, and the vehicle positioning and surrounding information processing module 205 includes a GPS and a surround view camera.
[0061] Furthermore, the vehicle collision sensor module 201 is used to monitor whether a collision has occurred. If it is determined that a collision has occurred, a positive feedback message is sent to the left front door control module 206.
[0062] The left front door opening sensor module 202 is used to monitor the opening information of the left front door. If it is determined that the left front door is closed, it sends a positive feedback message to the left front door control module 206.
[0063] The left front seat pressure sensor module 203 is used to monitor whether there is a driver on the left front seat. If it is determined that the pressure value on the left front seat is not less than the set threshold, a positive feedback message is sent to the left front door control module 206.
[0064] The left front door switch module 204 is used to monitor how the left front door opening command is obtained. If it is determined that the left front door opening command is triggered by the button on the outside of the door, a positive feedback message is sent to the left front door control module 206.
[0065] The vehicle positioning and surrounding information processing module is used to monitor the vehicle's location and the status information of people around the vehicle. If it is determined that the vehicle is in a road rage location and the people around it are in a road rage state, a positive feedback message is sent to module 206.
[0066] The left front door control module 206 is used to collect feedback information from the above modules. If all the received information is positive, the left front door control module 206 will refuse to execute the left front door opening command to protect the driver from road rage. Otherwise, the left front door control module 206 will agree to execute the left front door opening command.
[0067] Example 3
[0068] One embodiment of this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned safety identification vehicle control method based on multi-data fusion perception.
[0069] Example 4
[0070] One embodiment of this application provides a non-transitory computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, they implement the aforementioned safety identification vehicle control method based on multi-data fusion perception.
[0071] Example 5
[0072] One embodiment of this application provides an electronic device, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the aforementioned safety identification vehicle control method based on multi-data fusion perception.
[0073] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more flowchart illustrations and / or one or more block diagrams.
[0074] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.
[0075] While the specific embodiments of this application have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of this application. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of this application are still within the scope of protection of this application.
Claims
1. A safety identification vehicle control method based on multi-data fusion perception, characterized in that, include: Set preset conditions for activating the vehicle safety protection mechanism; The system acquires various sensor data from the vehicle, uses this data to identify the vehicle's safety status, and determines whether the identification results meet preset conditions. When all preset conditions are met, the vehicle safety protection mechanism is activated, and preset protection actions are implemented to protect the occupants. The preset conditions include a first preset condition, a second preset condition, a third preset condition, a fourth preset condition, and a fifth preset condition. The process of determining whether the fifth preset condition is met is as follows: acquire vehicle location information and external environment information, input the vehicle location information and external environment information into a probability-based road rage risk assessment model, identify and analyze the behavior of people outside the vehicle, determine whether there is harmful behavior based on the facial expressions and body movements of the identified people outside the vehicle, and if the output probability meets the probability threshold, it is determined that there is harmful behavior, and at this time the fifth preset condition is met.
2. The safety identification vehicle control method based on multi-data fusion perception as described in claim 1, characterized in that, The vehicle's various sensing data include vehicle driving data, left front door opening angle, left front seat pressure data, left front door opening / closing trigger signal, vehicle location information, and surrounding environment information.
3. The safety identification vehicle control method based on multi-data fusion perception as described in claim 1, characterized in that, Based on the status of the vehicle collision sensors, vehicle collision information is obtained to determine whether a collision has occurred. Vehicle driving data, including vehicle speed, distance to other vehicles, and road condition information, is also obtained. The vehicle speed, distance to other vehicles, and road condition information are analyzed through a neural network. Based on the current vehicle speed, the distance to the vehicle in front or the obstacle, and the road friction coefficient, the probability of a future vehicle collision is predicted. If the vehicle identification result is that no collision has occurred, then the first preset condition is met.
4. The safety identification vehicle control method based on multi-data fusion perception as described in claim 1, characterized in that, The opening angle of the left front door is obtained by measuring the status of the left front door opening sensor. The left front door is then determined to be closed based on the opening angle. If the left front door is closed, the second preset condition is met.
5. The safety identification vehicle control method based on multi-data fusion perception as described in claim 1, characterized in that, The driver's position information is obtained by the state of the left front seat pressure sensor to determine whether there is a driver in the left front seat. If there is a driver in the left front seat, the third preset condition is met. The trigger source of the left front door opening command is obtained by the trigger source state of the left front door switch. The trigger signal of the door switch is analyzed by a signal analysis algorithm to determine whether the left front door opening command is triggered by an external door button. If the left front door opening command is triggered by an external door button, the fourth preset condition is met.
6. The safety identification vehicle control method based on multi-data fusion perception as described in claim 1, characterized in that, The judgment results of five preset conditions are input into the decision tree node, and a decision is made through the pre-built decision tree model. When all preset conditions are met, the left front door of the vehicle cannot be opened.
7. A safety identification vehicle control system based on multi-data fusion perception, characterized in that, include: The initialization module is used to set the preset conditions for activating the vehicle safety protection mechanism; The control module is used to acquire various sensor data of the vehicle, use the various sensor data to identify the vehicle safety status, determine whether the identification result of the vehicle safety status meets the preset conditions, and when all preset conditions are met, the vehicle safety protection mechanism is activated and preset protection actions are implemented to protect the driver and passengers. The preset conditions include a first preset condition, a second preset condition, a third preset condition, a fourth preset condition, and a fifth preset condition. The process of determining whether the fifth preset condition is met is as follows: acquire vehicle location information and external environment information, input the vehicle location information and external environment information into a probability-based road rage risk assessment model, identify and analyze the behavior of people outside the vehicle, determine whether there is harmful behavior based on the facial expressions and body movements of the identified people outside the vehicle, and if the output probability meets the probability threshold, it is determined that there is harmful behavior, and at this time the fifth preset condition is met.
8. The safety identification vehicle control system based on multi-data fusion perception as described in claim 7, characterized in that, The vehicle's various sensing data include vehicle driving data, left front door opening angle, left front seat pressure data, left front door opening / closing trigger signal, vehicle location information, and surrounding environment information.
9. The safety identification vehicle control system based on multi-data fusion perception as described in claim 7, characterized in that, Based on the status of the vehicle collision sensors, vehicle collision information is obtained to determine whether a collision has occurred. Vehicle driving data, including vehicle speed, distance to other vehicles, and road condition information, is also obtained. The vehicle speed, distance to other vehicles, and road condition information are analyzed through a neural network. Based on the current vehicle speed, the distance to the vehicle in front or the obstacle, and the road friction coefficient, the probability of a future vehicle collision is predicted. If the vehicle identification result is that no collision has occurred, then the first preset condition is met.
10. The safety identification vehicle control system based on multi-data fusion perception as described in claim 7, characterized in that, The opening angle of the left front door is obtained by measuring the status of the left front door opening sensor. The left front door is then determined to be closed based on the opening angle. If the left front door is closed, the second preset condition is met.
11. The safety identification vehicle control system based on multi-data fusion perception as described in claim 7, characterized in that, The driver's position information is obtained by the state of the left front seat pressure sensor to determine whether there is a driver in the left front seat. If there is a driver in the left front seat, the third preset condition is met. The trigger source of the left front door opening command is obtained by the trigger source state of the left front door switch. The trigger signal of the door switch is analyzed by a signal analysis algorithm to determine whether the left front door opening command is triggered by an external door button. If the left front door opening command is triggered by an external door button, the fourth preset condition is met.
12. The safety identification vehicle control system based on multi-data fusion perception as described in claim 7, characterized in that, The judgment results of five preset conditions are input into the decision tree node, and a decision is made through the pre-built decision tree model. When all preset conditions are met, the left front door of the vehicle cannot be opened.
13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the safety identification vehicle control method based on multi-data fusion perception as described in claim 1.
14. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement the safety identification vehicle control method based on multi-data fusion perception as described in claim 1.
15. An electronic device, characterized in that, include: The device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory. When the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the safety identification vehicle control method based on multi-data fusion perception as described in claim 1.