Accident early warning system based on intelligent connected automobile

Abstract

The invention discloses an accident early warning system based on an intelligent networked automobile, particularly relates to the technical field of accident early warning, and realizes data interaction and transmission between the automobile and surrounding vehicles by collecting the driving states of the automobile and the surrounding vehicles in real time. And calculating the average speed and acceleration of surrounding vehicles through a weighted summation mode, and combining the average speed and acceleration with the data of the vehicle to obtain the speed and acceleration of the vehicle. Based on the information, the system calculates the safe distance to ensure that the safe distance is kept between the vehicle and the front vehicle. If the distance is smaller than the safe distance, the system sends out deceleration reminding. When the front vehicle is too close, the system predicts the driving tracks of the surrounding vehicles and the vehicle, simulates different turning angles and accelerations, and ensures that the vehicle does not collide with the surrounding vehicles. And if the avoidance turning is not feasible, the system simulates the collision momentum and the collision position in different obstacle avoidance modes, calculates a loss coefficient by using a logistic regression formula, and selects a risk avoidance path with the minimum loss, so that collision is effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of accident warning, and more specifically, to an accident warning system based on intelligent networked vehicles. Background Art

[0002] The accident warning system of intelligent connected vehicles (ICV) is based on the integration of intelligent, networked and information technologies, and aims to prevent and reduce traffic accidents through real-time data collection, analysis and prediction. With the advancement of automobile technology and the development of information network technology, the accident warning system of intelligent connected vehicles has become an important tool for improving road traffic safety.

[0003] Through advanced sensors, controllers, actuators and other devices, intelligent connected vehicles can perceive the surrounding environment in real time, make intelligent decisions, and achieve safe driving through collaborative control and execution; they can provide drivers and passengers with a more intelligent and convenient travel experience through integration with modern communication and network technologies; they can help reduce energy consumption and emissions by optimizing driving routes and improving traffic efficiency; they can realize information sharing between vehicles, improve road use efficiency and reduce traffic congestion.

[0004] In order to improve the accuracy of vehicle driving status detection and provide drivers with a safer avoidance path, the following scheme is proposed. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an accident warning system based on an intelligent networked vehicle to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: The accident warning system based on intelligent connected vehicles includes: perception module, communication module, data analysis module, warning module, risk avoidance module, data recording and feedback module; The perception module is used to obtain the driving status information of surrounding vehicles and the driving status information of the vehicle itself; The communication module is used to receive the driving status information of surrounding vehicles and send the driving status information of the vehicle itself; The data analysis module is used to determine the driving condition information of surrounding vehicles acquired by each sensor and the driving condition information sent by surrounding vehicles, and to perform weighted summing and averaging to obtain the average driving condition information of surrounding vehicles; and to perform weighted summing and averaging to obtain the average driving condition information of the own vehicle through the driving condition information sent by surrounding vehicles and the driving condition information of the own vehicle collected by the own vehicle; The warning module determines the safe distance based on the speed of the vehicle in front, the speed of the vehicle itself, and the deceleration acceleration of the vehicle itself. When the distance of the vehicle behind is close to the safe distance, the driver is reminded to brake and slow down. If the distance of the vehicle behind is less than the safe distance, the driver is reminded to accelerate. The risk avoidance module is used to calculate the loss coefficient by using the logistic regression formula based on the momentum and collision coefficient during collision under different driving paths, and select the path with the smallest loss coefficient as the risk avoidance path; The data recording and feedback module is used to record the data generated during the operation of the system.

[0007] In a preferred embodiment, the perception module obtains the driving status information of the vehicle and the driving status information of surrounding vehicles; the driving status of the vehicle includes the driving speed and acceleration of the vehicle; the driving status of surrounding vehicles includes the driving speed, acceleration, and distance from the vehicle of surrounding vehicles. The information obtained by the perception module is transmitted to the communication module and the data analysis module.

[0008] In a preferred embodiment, the communication module ensures real-time accident warning and traffic information sharing; at the same time, the communication module can also receive driving status information of surrounding vehicles and send the driving status information of the vehicle to surrounding vehicles.

[0009] In a preferred embodiment, the data analysis module is used to determine the surrounding vehicle driving condition information acquired by each sensor and the vehicle driving condition information sent by the surrounding vehicles, and perform weighted summing and averaging on the information to obtain the average surrounding vehicle driving condition information; the average vehicle driving condition information is obtained by weighted summing and averaging the vehicle driving information sent by the surrounding vehicles and the vehicle driving condition information collected by the vehicle, and the average surrounding vehicle driving condition information and the average vehicle driving condition information are transmitted to the early warning module and the risk avoidance module.

[0010] In a preferred embodiment, the warning module determines the safety distance by the speed of the vehicle ahead, the speed of the vehicle itself, and the deceleration acceleration of the vehicle itself; ; ;in Represents the vehicle speed; represents the speed of the vehicle ahead; t represents the time required for the vehicle to completely brake; a represents the deceleration acceleration of the vehicle; L represents the safe distance; When the current rear vehicle is close to the safe distance, the owner is reminded to brake and slow down. If the rear vehicle is less than the safe distance from the vehicle, the owner is reminded to accelerate.

[0011] In a preferred embodiment, the risk avoidance module is used to control the vehicle to turn if the distance between the current vehicle and the vehicle in front is less than the safe distance, predict the driving trajectory of the surrounding vehicles according to the speed and acceleration of the surrounding vehicles, and simulate the driving trajectory of the vehicle under different turning angles and different acceleration conditions through big data; compare the driving trajectory of the surrounding vehicles with the driving trajectory of the vehicle, and find the driving trajectory of the vehicle that does not overlap with the surrounding vehicles at the same time point; If the vehicle cannot avoid collision by turning around, the collision speed and collision position under different obstacle avoidance modes are simulated, and the momentum at the time of collision is calculated by multiplying the vehicle's own weight by the collision speed; different collision positions are set with different collision coefficients according to different structural positions, which are set by the vehicle designer; The momentum and collision coefficient at the time of collision are combined, the momentum and collision coefficient at the time of collision are normalized, and the loss coefficient is calculated by logistic regression: ;P is the loss coefficient; dl is the momentum at the time of collision; px represents the collision coefficient, α and β are logistic regression coefficients, and e is the natural base; Select the driving route with the smallest loss coefficient as the risk avoidance path.

[0012] In a preferred embodiment, the data recording and feedback module is used to record the data generated during the operation of the system; if a collision occurs, an alarm will be processed in a timely manner.

[0013] In a preferred embodiment, the specific steps of implementing the accident warning system based on intelligent connected vehicles are as follows: Step A1: The vehicle's sensors collect the driving status of surrounding vehicles and the vehicle's driving status in real time; Step A2: Real-time interactive transmission of data collected by sensors of the vehicle and surrounding vehicles; Step A3: The driving condition information of surrounding vehicles acquired by various sensors and the driving condition information sent by surrounding vehicles are weighted and averaged to obtain the average driving condition information of surrounding vehicles; Step A4: performing weighted summing and averaging of the vehicle driving information sent by surrounding vehicles and the vehicle driving condition information collected by the vehicle to obtain average vehicle driving condition information; Step A5: Determine the safe distance by the speed of the vehicle ahead, the speed of the vehicle, and the deceleration acceleration of the vehicle; Step A6: If the distance between the vehicle and the vehicle ahead is less than the safe distance, remind the vehicle owner to slow down; Step A7: If the distance between the front vehicle and the front vehicle is less than the safe distance, control the vehicle to turn, predict the driving trajectory of the surrounding vehicles according to the speed and acceleration of the surrounding vehicles, and simulate the driving trajectory of the vehicle under different turning angles and different acceleration conditions through big data; compare the driving trajectory of the surrounding vehicles with the driving trajectory of the vehicle, find a driving trajectory that does not overlap with the surrounding vehicles at the same time point, and control the vehicle to drive along the trajectory to avoid collision; Step A8: If the vehicle cannot avoid a collision by turning around, the loss coefficient is calculated by using a logistic regression formula by simulating the momentum and collision position at the time of collision under different obstacle avoidance modes; Step A9: Select the driving route with the smallest collision coefficient as the risk avoidance route. Technical effects and advantages of the present invention: The present invention collects the driving status of the vehicle and surrounding vehicles in real time, including information such as speed and acceleration, and first uses the vehicle sensors and surrounding vehicle sensors to obtain these data. Then, the data interaction and transmission between the vehicle and the surrounding vehicles are realized. The driving speed and acceleration of the surrounding vehicles are calculated by weighted summing and averaging, so as to obtain the average driving status of the surrounding vehicles. Similarly, the speed and acceleration of the vehicle are obtained by weighted averaging the data collected by the vehicle and the data sent by the surrounding vehicles. The safe distance is calculated based on these data to ensure that the vehicle maintains a safe distance with the vehicle in front. If the distance between the vehicle and the vehicle in front is less than the safe distance, the system will issue a deceleration reminder. When the distance between the vehicle in front is too close, the system predicts the driving trajectory of the surrounding vehicles and the trajectory of the vehicle, and combines the simulation of different turning angles and accelerations to ensure that the vehicle does not overlap with the surrounding vehicles and avoids collision. If turning is inevitable and there is a risk of collision, the loss coefficient will be calculated by simulating the collision momentum and collision position under different obstacle avoidance modes using a logistic regression formula. Finally, according to the collision coefficient, the driving path with the least loss is selected as the risk avoidance path to ensure driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 It is a structural schematic diagram of an accident warning system based on an intelligent network-connected vehicle of the present invention; Figure 2 The figure is a schematic diagram of the working process of the accident warning system based on intelligent networked vehicles of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are 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 are within the scope of protection of the present invention.

[0016] The present invention collects the driving status of the vehicle and surrounding vehicles in real time, including information such as speed and acceleration, and first uses the vehicle sensors and surrounding vehicle sensors to obtain these data. Then, the data interaction and transmission between the vehicle and the surrounding vehicles are realized. The driving speed and acceleration of the surrounding vehicles are calculated by weighted summing and averaging, so as to obtain the average driving status of the surrounding vehicles. Similarly, the speed and acceleration of the vehicle are obtained by weighted averaging the data collected by the vehicle and the data sent by the surrounding vehicles. The safe distance is calculated based on these data to ensure that the vehicle maintains a safe distance with the vehicle in front. If the distance between the vehicle and the vehicle in front is less than the safe distance, the system will issue a deceleration reminder. When the distance between the vehicle in front is too close, the system predicts the driving trajectory of the surrounding vehicles and the trajectory of the vehicle, and combines the simulation of different turning angles and accelerations to ensure that the vehicle does not overlap with the surrounding vehicles and avoids collision. If turning is inevitable and there is a risk of collision, the loss coefficient will be calculated by simulating the collision momentum and collision position under different obstacle avoidance modes using a logistic regression formula. Finally, according to the collision coefficient, the driving path with the least loss is selected as the risk avoidance path to ensure driving safety.

[0017] Example 1

[0018] The present invention discloses an accident warning system based on intelligent networked vehicles, such as Figure 1 As shown, it includes a perception module, a communication module, a data analysis module, an early warning module, a risk avoidance module, and a data recording and feedback module; The perception module is used to obtain the driving status information of surrounding vehicles and the driving status information of the vehicle itself; The communication module is used to receive the driving status information of surrounding vehicles and send the driving status information of the vehicle itself; The data analysis module is used to determine the driving condition information of surrounding vehicles acquired by each sensor and the driving condition information sent by surrounding vehicles, and to perform weighted summing and averaging to obtain the average driving condition information of surrounding vehicles; and to perform weighted summing and averaging to obtain the average driving condition information of the own vehicle through the driving condition information sent by surrounding vehicles and the driving condition information of the own vehicle collected by the own vehicle; The warning module determines the safe distance based on the speed of the vehicle in front, the speed of the vehicle itself, and the deceleration acceleration of the vehicle itself. When the distance of the vehicle behind is close to the safe distance, the driver is reminded to brake and slow down. If the distance of the vehicle behind is less than the safe distance, the driver is reminded to accelerate. The risk avoidance module is used to calculate the loss coefficient by using the logistic regression formula based on the momentum and collision coefficient during collision under different driving paths, and select the path with the smallest loss coefficient as the risk avoidance path; The data recording and feedback module is used to record the data generated during the operation of the system; if a collision occurs, an alarm will be issued in a timely manner.

[0019] The perception module obtains the driving status information of the vehicle and surrounding vehicles; the driving status of the vehicle includes the driving speed and acceleration of the vehicle; the driving status of surrounding vehicles includes the driving speed, acceleration and distance of surrounding vehicles from the vehicle. The information obtained by the perception module is transmitted to the communication module and the data analysis module.

[0020] Radar emits electromagnetic waves, which are reflected by obstacles and then return to the receiver. By calculating the reflection time of the waves, the distance between the object and the vehicle and the speed of surrounding vehicles can be measured; radar has strong penetrating power and can work in adverse weather conditions (such as rain, fog, snow, etc.).

[0021] Camera: Through visual recognition technology, the camera can capture the driving status of vehicles on the surrounding roads; Compare the two images taken by the left and right cameras through stereo matching algorithms (such as SGBM, Semi-Global Matching, etc.) to find the corresponding position of each feature point in the left and right images. Calculate the depth of the object (that is, the distance from the camera) through the known camera baseline (the distance between the two cameras), camera internal parameters and the parallax of the feature points. The specific formula is: ; Where D is the object distance, F is the baseline of the camera, that is, the distance between the left and right cameras; W is the focal length of the camera; w is the parallax of the corresponding point in the image.

[0022] Object tracking algorithms can track the movement of a vehicle through multiple frames and estimate its speed.

[0023] Select feature points: Use object detection algorithms (such as YOLO, SSD, etc.) to detect the features of the vehicle in each frame and mark the location of the vehicle.

[0024] Tracking objects: Use tracking algorithms (such as KLT Tracker, SORT, DeepSORT, etc.) to track the position of the vehicle in consecutive frames and calculate the displacement of the vehicle in each frame.

[0025] Calculate speed: Based on the change in the vehicle position in each frame of the image, combined with the time difference, the vehicle speed can be calculated. For example, the speed V can be calculated by the following formula: V=d / t; where d is the displacement of the vehicle between two consecutive frames of images; t is the time difference between the two frames of images.

[0026] Laser Radar (LiDAR): Through laser ranging technology, it generates high-precision three-dimensional point cloud maps to help vehicles accurately identify surrounding obstacles, other vehicles, pedestrians, etc. LiDAR has great advantages in high-precision and low-light environments.

[0027] Inertial Measurement Unit (IMU): used to detect dynamic information of the vehicle, including acceleration, speed and other data, to help evaluate the vehicle's motion state and predict potential collision risks. IMU obtains the vehicle's acceleration and speed data through sensors such as accelerometers and gyroscopes.

[0028] The communication module uses the low latency and high bandwidth characteristics of 5G communication to transmit data, ensuring real-time accident warning and traffic information sharing; at the same time, the communication module can also receive driving status information of surrounding vehicles and send the driving status information of the vehicle to surrounding vehicles.

[0029] The data analysis module is used to determine the driving condition information of surrounding vehicles acquired by each sensor and the driving condition information sent by surrounding vehicles, and to perform weighted summing and averaging to obtain the average driving condition information of surrounding vehicles; the weight of each sensor and the weight of the data sent by surrounding vehicles are set by the system, which can be set according to different sensor accuracy and detection distance. The average driving condition information of surrounding vehicles and the average driving condition information of the vehicle are transmitted to the early warning module and the risk avoidance module.

[0030] The warning module determines the safe distance based on the speed of the vehicle ahead, the speed of the vehicle itself, and the deceleration acceleration of the vehicle itself. The deceleration acceleration of the vehicle itself is obtained through experiments before the vehicle leaves the factory. ; ;in Represents the vehicle speed; represents the speed of the vehicle in front; t represents the time required for the vehicle to stop completely; a represents the deceleration acceleration of the vehicle; and L represents the safe distance.

[0031] When the current rear vehicle is close to the safe distance, the owner is reminded to brake and slow down. If the rear vehicle is less than the safe distance from the vehicle, the owner is reminded to accelerate.

[0032] The risk avoidance module controls the vehicle to turn if an emergency occurs, causing the distance between the current vehicle and the vehicle in front to be less than the safe distance. It predicts the driving trajectory of surrounding vehicles based on the speed and acceleration of surrounding vehicles, and simulates the driving trajectory of the vehicle under different turning angles and different acceleration conditions through big data. It compares the driving trajectory of surrounding vehicles with the driving trajectory of the vehicle, finds a driving trajectory that does not overlap with surrounding vehicles at the same time point, and controls the vehicle to drive along this trajectory to avoid collision.

[0033] If the vehicle cannot avoid a collision by turning around, the collision speed and collision position under different obstacle avoidance modes are simulated, and the momentum at the time of collision is calculated by multiplying the vehicle's own weight by the collision speed; different collision positions are set with different collision coefficients according to different structural positions, which are set by the vehicle designer.

[0034] The momentum and collision coefficient at the time of collision are combined and normalized. Specifically, the data is normalized using the following formula: Normalized to the range [0,1]: ;in is the normalized value, and Data The minimum and maximum values ​​of .

[0035] Calculate the loss coefficient via logistic regression: ;P is the loss coefficient; dl is the momentum at the time of collision, where the greater the momentum at the time of collision, the greater the loss coefficient, and vice versa; px represents the collision coefficient, the greater the collision coefficient, the greater the loss coefficient, and vice versa; α and β are logistic regression coefficients.

[0036] The driving route with the smallest loss coefficient is selected as the avoidance path, which causes the least harm to the driver and minimizes the harm to the driver in the event of an unavoidable collision.

[0037] The data recording and feedback module is used to record the data generated during the operation of the system to facilitate the subsequent accident assessment; if a collision occurs, an alarm will be issued in a timely manner.

[0038] The accident warning system of the present invention is based on the intelligent network vehicle. Figure 2 As shown, the specific steps are as follows: Step A1: The vehicle's sensors collect the driving status of surrounding vehicles and the vehicle's driving status in real time; Step A2: Real-time interactive transmission of data collected by sensors of the vehicle and surrounding vehicles; Step A3: The driving condition information of surrounding vehicles acquired by various sensors and the driving condition information sent by surrounding vehicles are weighted and averaged to obtain the average driving condition information of surrounding vehicles; Step A4: performing weighted summing and averaging of the vehicle driving information sent by surrounding vehicles and the vehicle driving condition information collected by the vehicle to obtain average vehicle driving condition information; Step A5: Determine the safe distance by the speed of the vehicle ahead, the speed of the vehicle, and the deceleration acceleration of the vehicle; Step A6: If the distance between the vehicle and the vehicle ahead is less than the safe distance, remind the vehicle owner to slow down; Step A7: If the distance between the front vehicle and the vehicle in front is less than the safe distance, control the vehicle to turn, predict the driving trajectory of the surrounding vehicles according to the speed and acceleration of the surrounding vehicles, and simulate the driving trajectory of the vehicle under different turning angles and different acceleration conditions through big data; compare the driving trajectory of the surrounding vehicles with the driving trajectory of the vehicle, find the driving trajectory of the vehicle that does not overlap with the surrounding vehicles at the same time point, and control the vehicle to drive along the trajectory to avoid collision.

[0039] Step A8: If the vehicle cannot avoid a collision by turning around, the loss coefficient is calculated by using a logistic regression formula by simulating the momentum and collision position at the time of collision under different obstacle avoidance modes; Step A9: Select a driving route with the smallest collision coefficient as an avoidance route.

[0040] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0041] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the units is only a logic.

[0042] Functional division, in actual implementation, there may be other division methods, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not performed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0043] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0044] In addition, each functional unit in each embodiment of the present application 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.

[0045] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An accident warning system based on intelligent connected vehicles, characterized in that: include: Perception module, communication module, data analysis module, early warning module, risk avoidance module, data recording and feedback module; The perception module is used to obtain the driving status information of surrounding vehicles and the driving status information of the vehicle itself; The communication module is used to receive the driving status information of surrounding vehicles and send the driving status information of the vehicle itself; The data analysis module is used to determine the driving condition information of surrounding vehicles acquired by each sensor and the driving condition information sent by surrounding vehicles, and to perform weighted summing and averaging to obtain the average driving condition information of surrounding vehicles; and to perform weighted summing and averaging to obtain the average driving condition information of the own vehicle through the driving condition information sent by surrounding vehicles and the driving condition information of the own vehicle collected by the own vehicle; The warning module determines the safe distance based on the speed of the vehicle in front, the speed of the vehicle itself, and the deceleration acceleration of the vehicle itself. When the distance of the vehicle behind is close to the safe distance, the driver is reminded to brake and slow down. If the distance of the vehicle behind is less than the safe distance, the driver is reminded to accelerate. The risk avoidance module is used to calculate the loss coefficient by using the logistic regression formula based on the momentum and collision coefficient during collision under different driving paths, and select the path with the smallest loss coefficient as the risk avoidance path; The data recording and feedback module is used to record the data generated during the operation of the system.

2. The accident warning system based on intelligent networked vehicles according to claim 1 is characterized in that: The perception module obtains the driving status information of the vehicle and the surrounding vehicles; the driving status of the vehicle includes the driving speed and acceleration of the vehicle; the driving status of the surrounding vehicles includes the driving speed, acceleration, and distance from the vehicle. The information obtained by the perception module is transmitted to the communication module and the data analysis module.

3. The accident warning system based on intelligent networked vehicles according to claim 1 is characterized in that: The communication module ensures real-time accident warning and traffic information sharing; at the same time, the communication module can also receive driving status information of surrounding vehicles and send the driving status information of the vehicle to surrounding vehicles.

4. The accident warning system based on intelligent networked vehicles according to claim 1 is characterized in that: The data analysis module is used to determine the driving condition information of surrounding vehicles acquired by each sensor and the driving condition information sent by surrounding vehicles, and to perform weighted summing and averaging on the information to obtain the average driving condition information of surrounding vehicles; the average driving condition information of the vehicle is obtained by weighted summing and averaging the driving condition information of the vehicle sent by surrounding vehicles and the driving condition information of the vehicle collected by the vehicle, and the average driving condition information of surrounding vehicles and the average driving condition information of the vehicle are transmitted to the early warning module and the risk avoidance module.

5. The accident warning system based on intelligent networked vehicles according to claim 1 is characterized in that: The warning module determines the safe distance based on the speed of the vehicle ahead, the speed of the vehicle itself, and the deceleration acceleration of the vehicle itself; ; ;in Represents the vehicle speed; Represents the speed of the vehicle ahead; t represents the time required for the vehicle to completely stop; a represents the deceleration acceleration of the vehicle; L represents the safe distance; When the current rear vehicle is close to the safe distance, the owner is reminded to brake and slow down. If the rear vehicle is less than the safe distance from the vehicle, the owner is reminded to accelerate.

6. The accident warning system based on intelligent networked vehicles according to claim 1 is characterized in that: The risk avoidance module is used to control the vehicle to turn if the distance between the current vehicle and the vehicle in front is less than the safe distance, predict the driving trajectory of surrounding vehicles based on the speed and acceleration of surrounding vehicles, and simulate the driving trajectory of the vehicle under different turning angles and different acceleration conditions through big data; compare the driving trajectory of surrounding vehicles with the driving trajectory of the vehicle, and find the driving trajectory of the vehicle that does not overlap with the surrounding vehicles at the same time point; If the vehicle cannot avoid collision by turning around, the collision speed and collision position under different obstacle avoidance modes are simulated, and the momentum at the time of collision is calculated by multiplying the vehicle's own weight by the collision speed; different collision positions are set with different collision coefficients according to different structural positions, which are set by the vehicle designer; The momentum and collision coefficient at the time of collision are combined, the momentum and collision coefficient at the time of collision are normalized, and the loss coefficient is calculated by logistic regression: ; P is the loss coefficient; dl is the momentum at the time of collision; px represents the collision coefficient, α and β are the logistic regression coefficients, and e is the natural base; Select the driving route with the smallest loss coefficient as the risk avoidance path.

7. The accident warning system based on intelligent networked vehicles according to claim 1 is characterized in that: The data recording and feedback module is used to record the data generated during the operation of the system; if a collision occurs, an alarm will be issued in a timely manner.

8. The accident warning system based on intelligent networked vehicles according to claim 1 is characterized in that: The specific steps of implementing the accident warning system based on intelligent connected vehicles are as follows: Step A1: The vehicle's sensors collect the driving status of surrounding vehicles and the vehicle's driving status in real time; Step A2: Real-time interactive transmission of data collected by sensors of the vehicle and surrounding vehicles; Step A3: The driving condition information of surrounding vehicles acquired by various sensors and the driving condition information sent by surrounding vehicles are weighted and averaged to obtain the average driving condition information of surrounding vehicles; Step A4: performing weighted summing and averaging of the vehicle driving information sent by surrounding vehicles and the vehicle driving condition information collected by the vehicle to obtain average vehicle driving condition information; Step A5: Determine the safe distance by the speed of the vehicle ahead, the speed of the vehicle, and the deceleration acceleration of the vehicle; Step A6: If the distance between the vehicle and the vehicle ahead is less than the safe distance, remind the vehicle owner to slow down; Step A7: If the distance between the front vehicle and the front vehicle is less than the safe distance, control the vehicle to turn, predict the driving trajectory of the surrounding vehicles according to the speed and acceleration of the surrounding vehicles, and simulate the driving trajectory of the vehicle under different turning angles and different acceleration conditions through big data; compare the driving trajectory of the surrounding vehicles with the driving trajectory of the vehicle, find a driving trajectory that does not overlap with the surrounding vehicles at the same time point, and control the vehicle to drive along the trajectory to avoid collision; Step A8: If the vehicle cannot avoid a collision by turning around, the loss coefficient is calculated by using a logistic regression formula by simulating the momentum and collision position at the time of collision under different obstacle avoidance modes; Step A9: Select a driving route with the smallest collision coefficient as an avoidance route.

Images