CN-121973807-A - Anti-collision early warning method and device for vehicle

CN121973807ACN 121973807 ACN121973807 ACN 121973807ACN-121973807-A

Abstract

The application discloses a vehicle anti-collision early warning method and device, which relate to the technical field of vehicle automatic control, and are characterized in that based on output data and multi-dimensional evaluation indexes corresponding to each sensor in a plurality of sensors, fusion weights corresponding to the sensors are determined, fusion results are obtained, the fusion results, road attribute information, external collaborative perception data and weather early warning information are integrated, comprehensive data are obtained, environmental change trend in future preset time period is predicted based on the comprehensive data, environmental situation grade corresponding to the environmental change trend is output, a detection strategy is determined, when the surrounding environment of a vehicle is determined to meet preset conditions of the environmental situation grade, the detection strategy is executed, the detection results are obtained, anti-collision early warning measures are determined according to the detection results and the comprehensive data, and the anti-collision early warning measures are output. Thus, the anti-collision effect is improved.

Inventors

JIANG CHENLEI
JI QINGHUI
DING DEFENG

Assignees

奇瑞汽车股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260128

Claims (10)

1. A vehicle collision-prevention early warning method, characterized by comprising: acquiring output data and a multi-dimensional evaluation index corresponding to each sensor in a plurality of sensors; Calculating to obtain real-time reliability coefficients corresponding to the sensors by using a fuzzy logic algorithm based on the multi-dimensional evaluation indexes; Based on the real-time reliability coefficient, a dynamic weight distribution model is constructed, and fusion weights corresponding to the sensors are output through the dynamic weight distribution model; Carrying out fusion processing on the output data of each sensor based on the fusion weights to obtain fusion results; acquiring road attribute information, external collaborative awareness data and weather early warning information of a road where a vehicle is currently located; Integrating the fusion result, the road attribute information, the external collaborative awareness data and the weather early warning information to obtain comprehensive data; Based on the comprehensive data, predicting an environmental change trend within a preset time length in the future by adopting a space-time sequence prediction algorithm, and outputting an environmental situation grade corresponding to the environmental change trend; Determining a detection strategy corresponding to the environmental situation level from a preset detection strategy library; When the surrounding environment of the vehicle is determined to meet the preset condition of the environment situation level, executing the detection strategy to obtain a detection result, wherein the detection result comprises speed information and position information of a target; determining collision risk indexes according to the detection results and the comprehensive data; Determining a collision risk level based on the collision risk index; And determining anti-collision early warning measures based on the collision risk level, and outputting the anti-collision early warning measures.
2. The vehicle anti-collision warning method according to claim 1, wherein the outputting, by the dynamic weight distribution model, the fusion weight corresponding to each sensor includes: if the output data of each sensor has no conflict, determining the fusion weight of each sensor according to the proportion of the real-time reliability coefficient corresponding to each sensor, and obtaining a first fusion weight; If the output data of each sensor has conflict, determining conflict data based on the output data, calculating the confidence coefficient of the conflict data based on the real-time reliability coefficient and a data consistency check result, and determining the fusion weight of each sensor based on the real-time reliability coefficient and the confidence coefficient.
3. The vehicle anti-collision pre-warning method according to claim 2, wherein the determining the fusion weight of each sensor based on the real-time reliability coefficient and the confidence level includes: The method comprises the steps of setting fusion weights of sensors, of which output data are conflict data, the confidence coefficient of the output data is higher than a preset confidence coefficient threshold value and the real-time reliability coefficient is higher than a preset real-time reliability coefficient threshold value, as second fusion weights, setting fusion weights of sensors, of which the output data are conflict data and the real-time reliability coefficient is not higher than the preset real-time reliability coefficient threshold value, and/or setting fusion weights of sensors, of which the output data are conflict data and the confidence coefficient of the output data is not higher than the preset confidence coefficient threshold value, as third fusion weights, and determining fusion weights of sensors, of which the output data are not conflict data, based on the second fusion weights and the third fusion weights, wherein the second fusion weights are larger than the first fusion weights, and the third fusion weights are smaller than the first fusion weights.
4. The vehicle collision avoidance warning method according to claim 1, characterized in that, when it is determined that the surrounding environment of the vehicle satisfies the preset condition of the environmental situation level, the detection strategy is executed, and after the detection result is obtained, further comprising: Determining the detection deviation of the detection result and the real detection result; and adjusting the detection strategy based on the detection deviation.
5. The vehicle collision-prevention warning method according to claim 1, wherein the collision risk index includes a collision time and a collision distance, and the determining the collision risk index from the detection result and the integrated data includes: according to the detection result and the comprehensive data, the collision risk index is calculated by using the following formula: Wherein the target distance is the distance of the target from the vehicle.
6. The vehicle collision avoidance warning method of claim 1 wherein said determining a collision risk level based on said collision risk indicator comprises: when the range of the collision time is a first preset time range or the range of the collision distance is a first preset distance range, determining that the current collision risk level is a first-level collision risk level; When the range of the collision time is a second preset time range or the range of the collision distance is a second preset distance range, determining that the current collision risk level is a second collision risk level; And when the range of the collision time is a third preset time range or the range of the collision distance is a third preset distance range, determining that the current collision risk level is a three-level collision risk level.
7. The vehicle collision avoidance early warning method of claim 6 wherein said determining a collision avoidance early warning measure based on said collision risk level comprises: if the current collision risk level is the primary collision risk level, reminding a driver through an indicator lamp and beeping sounds on the instrument panel; if the front collision risk level is the secondary collision risk level, controlling the vehicle to brake, and reducing the vehicle speed; and if the current collision risk level is the three-level collision risk level, determining emergency braking and steering avoidance measures.
8. A vehicle collision-prevention warning device, characterized by comprising: the first acquisition module is used for acquiring output data and a multi-dimensional evaluation index corresponding to each sensor in the plurality of sensors; the calculation module is used for calculating and obtaining real-time reliability coefficients corresponding to the sensors by using a fuzzy logic algorithm based on the multi-dimensional evaluation index; The construction module is used for constructing a dynamic weight distribution model based on the real-time reliability coefficient, and outputting fusion weights corresponding to the sensors through the dynamic weight distribution model; the fusion module is used for carrying out fusion processing on the output data of each sensor based on the fusion weights to obtain fusion results; The second acquisition module is used for acquiring road attribute information, external collaborative awareness data and weather early warning information of a road where the vehicle is currently located; The integration module is used for integrating the fusion result, the road attribute information, the external collaborative awareness data and the weather early warning information to obtain comprehensive data; the prediction module is used for predicting the environmental change trend within the future preset duration by adopting a space-time sequence prediction algorithm based on the comprehensive data and outputting an environmental situation grade corresponding to the environmental change trend; The first determining module is used for determining a detection strategy corresponding to the environment situation level from a preset detection strategy library; The execution module is used for executing the detection strategy to obtain a detection result when the surrounding environment of the vehicle is determined to meet the preset condition of the environment situation level, wherein the detection result comprises speed information and position information of a target; The second determining module is used for determining collision risk indexes according to the detection results and the comprehensive data; A third determining module, configured to determine a collision risk level based on the collision risk indicator; and the fourth determining module is used for determining anti-collision early warning measures based on the collision risk level and outputting the anti-collision early warning measures.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the vehicle collision warning method of any one of claims 1-7 when the computer program is executed.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the vehicle collision warning method according to any one of claims 1 to 7.

Description

Anti-collision early warning method and device for vehicle Technical Field The application relates to the technical field of automatic control of vehicles, in particular to an anti-collision early warning method and device for vehicles. Background In the related technology, the existing anti-collision early warning method of the automobile automatic driving system has the defects that in the aspect of early warning precision, analysis and judgment are mostly carried out based on single sensor data, the early warning precision is easy to influence by the precision of the sensor and environmental factors, so that the early warning precision is low, false alarm or missing alarm is often caused, meanwhile, under the condition of rainy weather and extreme environments, such as heavy rain, heavy snow, heavy fog, strong light irradiation and the like, the performance of the sensor is seriously influenced, a camera is easily shielded by the rainy water in the rainy weather, so that images are fuzzy, the front obstacle cannot be accurately identified, the transmission of electromagnetic waves is disturbed by the radar in the heavy fog weather, the detection precision and the distance are greatly reduced, and the anti-collision early warning effect is poor. Disclosure of Invention In view of the above, the application provides a vehicle anti-collision early warning method and device, which are used for solving the problem of poor anti-collision effect in the prior art. The aim of the application can be achieved by the following technical scheme: the first aspect of the application provides a vehicle anti-collision early warning method, which comprises the following steps: Acquiring output data and a multi-dimensional evaluation index corresponding to each sensor in the plurality of sensors; Based on the multidimensional evaluation index, calculating to obtain real-time reliability coefficients corresponding to the sensors by using a fuzzy logic algorithm; based on the real-time reliability coefficient, a dynamic weight distribution model is constructed, and fusion weights corresponding to the sensors are output through the dynamic weight distribution model; carrying out fusion processing on the output data of each sensor based on the fusion weight to obtain a fusion result; acquiring road attribute information, external collaborative awareness data and weather early warning information of a road where a vehicle is currently located; integrating the fusion result, the road attribute information, the external collaborative awareness data and the weather early warning information to obtain comprehensive data; based on the comprehensive data, predicting the environmental change trend within a preset time length in the future by adopting a space-time sequence prediction algorithm, and outputting an environmental situation grade corresponding to the environmental change trend; Determining a detection strategy corresponding to the environmental situation level from a preset detection strategy library; When the surrounding environment of the vehicle is determined to meet the preset condition of the environment situation level, executing a detection strategy to obtain a detection result, wherein the detection result comprises speed information and position information of a target; Determining collision risk indexes according to the detection result and the comprehensive data; determining a collision risk level based on the collision risk index; and determining anti-collision early warning measures based on the collision risk level, and outputting the anti-collision early warning measures. In an alternative embodiment, outputting the fusion weight corresponding to each sensor through the dynamic weight distribution model includes: If the output data of each sensor has no conflict, determining the fusion weight of each sensor according to the proportion of the real-time reliability coefficient corresponding to each sensor, and obtaining a first fusion weight; if the output data of each sensor has conflict, the conflict data is determined based on the output data, the confidence coefficient of the conflict data is calculated based on the real-time reliability coefficient and the data consistency check result, and the fusion weight of each sensor is determined based on the real-time reliability coefficient and the confidence coefficient. In an alternative embodiment, determining fusion weights for each sensor based on the real-time reliability coefficients and confidence comprises: The method comprises the steps of setting fusion weights of sensors with output data being conflict data, confidence coefficient of the output data being higher than a preset confidence coefficient threshold and real-time reliability coefficient being higher than the preset real-time reliability coefficient threshold as second fusion weights, setting fusion weights of sensors with output data being conflict data and real-time reliability coefficient no