Electric four-wheeler vehicle collision safety early warning system based on artificial intelligence

By using artificial intelligence technology in the vehicle collision safety warning system, real-time data of vehicles and obstacles are collected, relative speed and expected collision time are calculated, and early warning signals are generated, the problem of inaccurate image analysis in the existing technology is solved and the system is improved security and accuracy.

CN118928383AInactive Publication Date: 2024-11-12SHANDONG JIACHI NEW ENERGY AUTOMOBILE TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411196499.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing vehicle collision safety warning system relies on image analysis and is susceptible to environmental impact, resulting in inaccurate judgments and reducing the safety of the system.

Method used

Using an electric four-wheeled vehicle collision safety warning system based on artificial intelligence, the vehicle data acquisition module, data analysis module and self-intervention module are used to collect the vehicle's real-time speed, obstacle data and head orientation angle, and calculate the relative speed and expected collision time. Generate a safe distance warning signal or automatic deceleration signal to reduce the impact of the environment on image analysis.

Benefits of technology

It improves the safety of the vehicle collision safety warning system, ensures driving safety, avoids the error of judging vehicle distances by relying solely on image analysis, and enhances the accuracy and reliability of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118928383A_ABST
    Figure CN118928383A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of vehicle safety, and discloses an electric four-wheeler vehicle collision safety early warning system based on artificial intelligence. According to the electric four-wheeler vehicle collision safety pre-warning system based on artificial intelligence, the real-time speed data of a vehicle, the real-time data of an obstacle and the degree of the current vehicle head orientation of the vehicle are collected, and the first collision estimated time and the second collision estimated time are calculated according to whether the vehicle and the obstacle are in straight line driving or not; and a safety distance early warning signal or an automatic deceleration signal or a linear safety distance early warning signal or an automatic deceleration signal II is correspondingly generated, the signals are sent to the self-intervention module, and the self-intervention module gives out an early warning to prompt a driver to pay attention to or take active braking measures, so that the driving safety is ensured, and the driving safety is improved. The situation that the vehicle distance between the vehicle and other objects is judged only through image analysis is avoided, the influence of the environment on vehicle distance judgment through vehicle image analysis is reduced, and then the safety of the vehicle collision safety early warning system is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle safety technology, and in particular to an electric four-wheel vehicle collision safety warning system based on artificial intelligence. Background Art

[0002] Electric four-wheeled vehicles, referred to as electric vehicles (EV), are vehicles that use electricity as the main power source. Unlike traditional internal combustion engine vehicles, electric four-wheeled vehicles are driven by electric motors instead of internal combustion engines. They are usually divided into battery electric vehicles (BEV), plug-in hybrid electric vehicles (PHEV) and range extended electric vehicles (REEV). The electric four-wheeled vehicle collision safety warning system based on artificial intelligence is an advanced technology designed to improve vehicle safety and reduce collision accidents;

[0003] At present, vehicle collision safety warning systems usually use image recognition to determine whether there is an obstacle in front of the vehicle, and determine whether the vehicle is close to the obstacle based on image information collected from the front and back. However, image analysis is easily affected by the actual environment in which the vehicle is located and cannot make correct judgments, thereby reducing the safety of the vehicle collision safety warning system. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides an electric four-wheel vehicle collision safety warning system based on artificial intelligence, which has the advantages of avoiding relying solely on image analysis to determine the distance between the vehicle and other objects, reducing the impact of the environment on the vehicle image analysis to determine the distance, thereby improving the safety of the vehicle collision safety warning system, and solving the above-mentioned problems.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an artificial intelligence-based electric four-wheel vehicle collision safety warning system, comprising a vehicle data acquisition module, a vehicle data analysis module and a self-intervention module;

[0008] The vehicle data acquisition module includes a vehicle speed acquisition unit, a vehicle environment acquisition unit and a vehicle angle acquisition unit;

[0009] The vehicle speed acquisition unit is used to acquire the vehicle's real-time speed data sd, and the vehicle environment acquisition unit is used to acquire the obstacle data in front of the vehicle. The superscript (x, y) represents the two-dimensional coordinates of the current position of the vehicle, v represents the real-time speed data of the obstacle in front of the vehicle, and the subscript d represents the distance between the obstacle and the vehicle. The vehicle angle acquisition unit is used to acquire the current vehicle head orientation angle data JD. The vehicle data acquisition module collects the real-time vehicle speed data sd and the obstacle data in front of the vehicle. And the current vehicle head direction angle data JD is sent to the vehicle data analysis module;

[0010] The vehicle data analysis module collects the vehicle's front obstacle data based on the vehicle's real-time speed data sd Calculate the relative speed Sv between the vehicle and the obstacle. When the vehicle is traveling in a straight line, the vehicle data analysis module calculates the estimated collision time Sj according to the relative speed Sv and the distance between the obstacle and the vehicle. z and compare it with the collision prediction time-threshold Sjyz z When the vehicle is in a different direction from the obstacle, the vehicle data analysis module calculates the relative speed Sv2 according to the current vehicle head direction angle data JD, the vehicle real-time speed data sd and the real-time speed data of the obstacle in front of the vehicle, and calculates the collision prediction time Sj according to the relative speed Sv2. e and compare it with the collision estimated time second threshold Sjyz e Compare and generate a safety distance warning signal or an automatic deceleration signal;

[0011] The vehicle data analysis module sends the generated straight-line safety distance warning signal or automatic deceleration signal or safety distance warning signal or automatic deceleration signal 2 to the self-intervention module;

[0012] The self-intervention module controls vehicle braking or issues a warning to the driver according to the received signal.

[0013] Preferably, the relative speed Sv between the vehicle and the obstacle is calculated as follows:

[0014] Sv=sd-v

[0015] In the formula, sd represents the current real-time speed data of the vehicle, v represents the current real-time speed data of the obstacle in front of the vehicle, and sd-v represents the difference between the two, that is, the relative speed Sv between the vehicle and the obstacle.

[0016] Preferably, the collision prediction time is Sj z The calculation expression is as follows:

[0017]

[0018] In the formula, d is the current distance between the obstacle and the vehicle, Indicates that at the current distance, the time it takes for the vehicle to reach the obstacle is the estimated collision time - Sj z .

[0019] Preferably, the relative speed Sv2 is calculated as follows:

[0020]

[0021] In the formula, sd 2 、v 2 They respectively represent the square of the vehicle's current real-time speed data and the square of the obstacle's current real-time speed data. 2sd*v*cos(JD) represents the product of the components of the vehicle's current real-time speed data and the obstacle's current real-time speed data in the same direction. The square root operation yields the relative speed Sv2.

[0022] Preferably, the collision prediction time is Sj e The calculation expression is as follows:

[0023]

[0024] In the formula, d is the current distance between the obstacle and the vehicle, The time it takes for the vehicle to reach the obstacle at the current distance is the estimated collision time Sj e .

[0025] Preferably, the vehicle data analysis module calculates the estimated collision time Sj z and collision prediction time-threshold Sjyz z By contrast, when the collision prediction time is Sj z Greater than the collision prediction time threshold Sjyz z The vehicle data analysis module generates a straight-line safety distance warning signal when the collision estimated time is Sj z Less than the collision prediction time threshold Sjyz z , the vehicle data analysis module generates an automatic deceleration signal.

[0026] Preferably, the vehicle data analysis module calculates the estimated collision time Sj. e and the collision estimated time second threshold Sjyz e By contrast, when the collision estimated time is equal to Sj e Greater than the second threshold of the estimated collision time Sjyz eWhen the vehicle data analysis module generates a safety distance warning signal, the collision prediction time is equal to Sj. e Less than the second threshold of the estimated collision time Sjyz e When the vehicle data analysis module generates an automatic deceleration signal 2.

[0027] Preferably, the vehicle data analysis module sends the generated straight-line safety distance warning signal or automatic deceleration signal to the self-intervention module.

[0028] Preferably, the vehicle data analysis module sends the generated safety distance warning signal or automatic deceleration signal 2 to the self-intervention module.

[0029] Preferably, when the self-intervention module receives a straight-line safety distance warning signal or a safety distance warning signal or receives both signals at the same time, the self-intervention module generates a warning signal and issues a warning to the driver;

[0030] When the self-intervention module receives an automatic deceleration signal or any one of the two automatic deceleration signals, the self-intervention module generates a braking signal and controls the vehicle to brake and decelerate.

[0031] Compared with the prior art, the present invention provides an electric four-wheel vehicle collision safety warning system based on artificial intelligence, which has the following beneficial effects:

[0032] The present invention collects the real-time speed data of the vehicle, the real-time data of the obstacle and the degree of the current front direction of the vehicle, and calculates the collision prediction time 1 and the collision prediction time 2 respectively according to whether the vehicle and the obstacle are in a straight line, and compares the collision prediction time 1 or the collision prediction time 2 with the corresponding threshold value, and generates a safety distance warning signal or an automatic deceleration signal or a straight-line safety distance warning signal or an automatic deceleration signal 2 accordingly, and sends these signals to the self-intervention module, and issues a warning through the self-intervention module to prompt the driver to pay attention or take active braking measures to ensure driving safety, avoid relying solely on image analysis to judge the distance between the vehicle and other objects, reduce the influence of the environment on the vehicle image analysis to judge the distance, and thus improve the safety of the vehicle collision safety warning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0034] 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.

[0035] See also Figure 1 , an electric four-wheel vehicle collision safety warning system based on artificial intelligence, including a vehicle data acquisition module, a vehicle data analysis module and a self-intervention module.

[0036] The vehicle data acquisition module includes a vehicle speed acquisition unit, a vehicle environment acquisition unit, and a vehicle angle acquisition unit. The functions of these units are as follows:

[0037] The vehicle speed collection unit is used to collect the vehicle real-time speed data sd;

[0038] The vehicle environment acquisition unit is used to collect obstacle data in front of the vehicle Among them, the superscript (x, y) represents the two-dimensional coordinates of the vehicle's current position, v represents the real-time speed data of the obstacle in front of the vehicle, and the subscript d represents the distance between the obstacle and the vehicle;

[0039] The vehicle angle acquisition unit is used to acquire the current vehicle front heading angle data JD;

[0040] The vehicle data acquisition module collects the real-time vehicle speed data sd and the obstacle data in front of the vehicle The vehicle's current head angle data JD is sent to the vehicle data analysis module for subsequent calculations to estimate and determine whether the vehicle will collide during driving;

[0041] When the vehicle is traveling in a straight line, the vehicle data analysis module collects the vehicle's real-time speed data SD and the obstacle data in front of the vehicle. Calculate the relative speed Sv between the vehicle and the obstacle, and the calculation formula is as follows:

[0042] Sv=sd-v

[0043] In the formula, sd represents the current real-time speed data of the vehicle, v represents the current real-time speed data of the obstacle in front of the vehicle, and sd-v represents the difference between the two, that is, the relative speed Sv between the vehicle and the obstacle.

[0044] After the relative speed Sv between the vehicle and the obstacle is calculated, the vehicle data analysis module calculates the estimated collision time Sj according to the relative speed Sv and the distance between the obstacle and the vehicle. z , and its calculation expression is as follows:

[0045]

[0046] In the formula, d is the current distance between the obstacle and the vehicle, Indicates that at the current distance, the time it takes for the vehicle to reach the obstacle is the estimated collision time - Sj z .

[0047] The vehicle data analysis module calculates the estimated collision time Sj based on the relative speed Sv and the distance between the obstacle and the vehicle. z and compare it with the collision prediction time-threshold Sjyz z In contrast, when the collision estimated time is Sj z Greater than the collision prediction time threshold Sjyz z The vehicle data analysis module generates a straight-line safety distance warning signal. When the collision estimated time is Sj z Less than the collision prediction time threshold Sjyz z , the vehicle data analysis module generates an automatic deceleration signal.

[0048] When the vehicle is in a different direction from the obstacle, the vehicle data analysis module calculates the relative speed Sv2 according to the current vehicle head direction angle data JD, the vehicle real-time speed data sd and the real-time speed data of the obstacle in front of the vehicle. The calculation expression is as follows:

[0049]

[0050] In the formula, sd 2 、v 2 They respectively represent the square of the vehicle's current real-time speed data and the square of the obstacle's current real-time speed data. 2sd*v*cos(JD) represents the product of the components of the vehicle's current real-time speed data and the obstacle's current real-time speed data in the same direction. The square root operation yields the relative speed Sv2.

[0051] After the relative speed Sv2 is calculated, the vehicle data analysis module calculates the estimated collision time Sj according to the relative speed Sv2. e , and its calculation expression is as follows:

[0052]

[0053] In the formula, d is the current distance between the obstacle and the vehicle, The time it takes for the vehicle to reach the obstacle at the current distance is the estimated collision time Sj e ;

[0054] The vehicle data analysis module converts the estimated collision time into Sje and the collision estimated time second threshold Sjyz e In contrast, when the collision estimated time is Sj e Greater than the second threshold of the estimated collision time Sjyz e When the estimated collision time is equal to Sj, the vehicle data analysis module generates a safety distance warning signal. e Less than the second threshold of the estimated collision time Sjyz e When the vehicle data analysis module generates automatic deceleration signal 2.

[0055] The vehicle data analysis module sends the generated straight-line safety distance warning signal or automatic deceleration signal to the self-intervention module, and the vehicle data analysis module sends the generated safety distance warning signal or automatic deceleration signal 2 to the self-intervention module;

[0056] The self-intervention module controls the vehicle braking or issues a warning to the driver according to the received signal. Specifically, when the self-intervention module receives a straight-line safety distance warning signal or a safety distance warning signal or receives both signals at the same time, the self-intervention module generates a warning signal and issues a warning to the driver;

[0057] When the self-intervention module receives the automatic deceleration signal or any one of the two automatic deceleration signals, the self-intervention module generates a braking signal and controls the vehicle to brake and decelerate.

[0058] By collecting the real-time speed data of the vehicle, the real-time data of the obstacle and the degree of the current front direction of the vehicle, the estimated collision time 1 and the estimated collision time 2 are calculated respectively according to whether the vehicle is traveling in a straight line with the obstacle, and the estimated collision time 1 or the estimated collision time 2 is compared with the corresponding threshold value, and a safety distance warning signal or an automatic deceleration signal or a straight-line safety distance warning signal or an automatic deceleration signal 2 is generated accordingly, and these signals are sent to the self-intervention module, and a warning is issued through the self-intervention module to prompt the driver to pay attention or take active braking measures to ensure driving safety, avoid relying solely on image analysis to judge the distance between the vehicle and other objects, reduce the impact of the environment on the vehicle image analysis to judge the distance, and thereby improve the safety of the vehicle collision safety warning system.

[0059] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An electric four-wheel vehicle collision safety warning system based on artificial intelligence, characterized in that: It includes a vehicle data acquisition module, a vehicle data analysis module and a self-intervention module; The vehicle data acquisition module includes a vehicle speed acquisition unit, a vehicle environment acquisition unit and a vehicle angle acquisition unit; The vehicle speed acquisition unit is used to acquire the vehicle's real-time speed data sd, and the vehicle environment acquisition unit is used to acquire the obstacle data in front of the vehicle. The superscript (x, y) represents the two-dimensional coordinates of the current position of the vehicle, v represents the real-time speed data of the obstacle in front of the vehicle, and the subscript d represents the distance between the obstacle and the vehicle. The vehicle angle acquisition unit is used to acquire the current vehicle head orientation angle data JD. The vehicle data acquisition module collects the real-time vehicle speed data sd and the obstacle data in front of the vehicle. And the current vehicle head direction angle data JD is sent to the vehicle data analysis module; The vehicle data analysis module collects the vehicle's front obstacle data based on the vehicle's real-time speed data sd Calculate the relative speed Sv between the vehicle and the obstacle. When the vehicle is traveling in a straight line, the vehicle data analysis module calculates the estimated collision time Sj according to the relative speed Sv and the distance between the obstacle and the vehicle. z and compare it with the collision prediction time-threshold Sjyz z When the vehicle is in a different direction from the obstacle, the vehicle data analysis module calculates the relative speed Sv2 according to the current vehicle head direction angle data JD, the vehicle real-time speed data sd and the real-time speed data of the obstacle in front of the vehicle, and calculates the collision prediction time Sj according to the relative speed Sv2. e and compare it with the collision estimated time second threshold Sjyz e Compare and generate a safety distance warning signal or an automatic deceleration signal; The vehicle data analysis module sends the generated straight-line safety distance warning signal or automatic deceleration signal or safety distance warning signal or automatic deceleration signal 2 to the self-intervention module; The self-intervention module controls vehicle braking or issues a warning to the driver according to the received signal.

2. The electric four-wheel vehicle collision safety warning system based on artificial intelligence according to claim 1 is characterized in that: The relative speed Sv between the vehicle and the obstacle is calculated as follows: Sv=sd-v In the formula, sd represents the current real-time speed data of the vehicle, v represents the current real-time speed data of the obstacle in front of the vehicle, and sd-v represents the difference between the two, that is, the relative speed Sv between the vehicle and the obstacle.

3. The electric four-wheel vehicle collision safety warning system based on artificial intelligence according to claim 2 is characterized in that: The collision prediction time Sj z The calculation expression is as follows: In the formula, d is the current distance between the obstacle and the vehicle, Indicates that at the current distance, the time it takes for the vehicle to reach the obstacle is the estimated collision time - Sj z .

4. The electric four-wheel vehicle collision safety warning system based on artificial intelligence according to claim 3 is characterized in that: The relative speed Sv2 is calculated as follows: In the formula, sd 2 、v 2 They respectively represent the square of the vehicle's current real-time speed data and the square of the obstacle's current real-time speed data. 2sd*v*cos(JD) represents the product of the components of the vehicle's current real-time speed data and the obstacle's current real-time speed data in the same direction. The square root operation yields the relative speed Sv2.

5. The electric four-wheel vehicle collision safety warning system based on artificial intelligence according to claim 4 is characterized in that: The estimated collision time is Sj e The calculation expression is as follows: In the formula, d is the current distance between the obstacle and the vehicle, The time it takes for the vehicle to reach the obstacle at the current distance is the estimated collision time Sj e .

6. The electric four-wheel vehicle collision safety warning system based on artificial intelligence according to claim 5 is characterized in that: The vehicle data analysis module calculates the estimated collision time Sj z and collision prediction time-threshold Sjyz z By contrast, when the collision prediction time is Sj z Greater than the collision prediction time threshold Sjyz z The vehicle data analysis module generates a straight-line safety distance warning signal when the collision estimated time is Sj z Less than the collision prediction time threshold Sjyz z , the vehicle data analysis module generates an automatic deceleration signal.

7. The electric four-wheel vehicle collision safety warning system based on artificial intelligence according to claim 6 is characterized in that: The vehicle data analysis module calculates the estimated collision time Sj e and the collision estimated time second threshold Sjyz e By contrast, when the collision estimated time is equal to Sj e Greater than the second threshold of the estimated collision time Sjyz e When the vehicle data analysis module generates a safety distance warning signal, the collision prediction time is equal to Sj. e Less than the second threshold of the estimated collision time Sjyz e When the vehicle data analysis module generates an automatic deceleration signal 2.

8. The electric four-wheel vehicle collision safety warning system based on artificial intelligence according to claim 7 is characterized in that: The vehicle data analysis module sends the generated straight-line safety distance warning signal or automatic deceleration signal to the self-intervention module.

9. The electric four-wheel vehicle collision safety warning system based on artificial intelligence according to claim 8 is characterized in that: The vehicle data analysis module sends the generated safety distance warning signal or automatic deceleration signal 2 to the self-intervention module.

10. The electric four-wheel vehicle collision safety warning system based on artificial intelligence according to claim 9 is characterized in that: When the self-intervention module receives a straight-line safety distance warning signal or a safety distance warning signal or receives both signals at the same time, the self-intervention module generates a warning signal and issues a warning to the driver; When the self-intervention module receives an automatic deceleration signal or any one of the two automatic deceleration signals, the self-intervention module generates a braking signal and controls the vehicle to brake and decelerate.

Citation Information

Cited By

  • Optimization control method, system and device for AI-driven new energy automobile power system

    CN120439815A