CN-121973793-A - Driving style recognition method, driving style recognition device, vehicle and storage medium

CN121973793ACN 121973793 ACN121973793 ACN 121973793ACN-121973793-A

Abstract

The embodiment of the application provides a driving style identification method, a driving style identification device, a vehicle and a storage medium. The method comprises the steps of obtaining a basic value of a driving style parameter of a driver of a vehicle through a pre-trained driving style model, obtaining a driving parameter of a neighboring vehicle of the vehicle, determining an offset value of the driving style parameter of the driver based on the driving parameter of the neighboring vehicle of the vehicle, and determining the driving style parameter of the driver based on the basic value of the driving style parameter and the offset value of the driving style parameter. According to the technical scheme provided by the embodiment of the application, the influence of the driving environment on the driving style of the driver is fully considered, so that the finally determined driving style parameters have stronger consistency under different driving environments, and the actual driving style of the driver is more attached when the vehicle is controlled to run according to the determined driving style parameters, thereby meeting the personalized driving requirement of the driver.

Inventors

WANG KAIZHENG
DI HUANYU
HUANG ZIHAO
Zhong Guoqi

Assignees

广州汽车集团股份有限公司

Dates

Publication Date: 20260505
Application Date: 20251224

Claims (11)

1. A driving style recognition method, characterized in that the method comprises: obtaining a basic value of a driving style parameter of a driver of the vehicle through a pre-trained driving style model; Acquiring running parameters of adjacent vehicles of the vehicle; Determining an offset value of a driving style parameter of the driver based on a driving parameter of a neighboring vehicle of the vehicle; a driving style parameter of the driver is determined based on the base value of the driving style parameter and an offset value of the driving style parameter.
2. The method of claim 1, wherein the determining an offset value of the driving style parameter of the driver based on the state parameter of the vehicle's neighborhood comprises: Constructing a driving risk field of the adjacent vehicle based on driving parameters of the adjacent vehicle of the vehicle and a pre-constructed driving risk field model, wherein the driving risk field model is a model for quantifying risks in the driving process of the vehicle through the driving parameters of the vehicle, the driving parameters of the adjacent vehicle and the interaction relationship between the vehicle and the adjacent vehicle; Determining relative parameters based on the driving risk field of the adjacent vehicle; determining weights of the relative parameters; an offset value of the driving style parameter is determined based on the relative parameter and the weight of the relative parameter.
3. The method of claim 2, wherein the determining the relative parameters based on the driving risk field of the neighboring vehicle comprises: determining a risk envelope of the adjacent vehicle based on a driving risk field of the adjacent vehicle, wherein the risk envelope of the adjacent vehicle refers to a curve that the risk value of the vehicle relative to the adjacent vehicle is larger than a preset value; Dividing an area determined based on the vehicle into a plurality of subareas when a plurality of adjacent vehicles exist; Determining, for each sub-region of the plurality of sub-regions, a distance between the vehicle and a risk envelope of neighboring vehicles within the sub-region; the relative parameter is determined based on a minimum value of a distance between the vehicle and a risk envelope of neighboring vehicles within the sub-area.
4. The method of claim 2, wherein the determining the weight of the relative parameter comprises: The weight of the relative parameter is determined based on a preset mapping relation, the speed of the vehicle, the relative speed of the target adjacent vehicle and the relative parameter, wherein the preset mapping relation comprises mapping relations among different speeds of the vehicle, different relative speeds of the target adjacent vehicle and the vehicle and different weights, and the target adjacent vehicle refers to an adjacent vehicle with the minimum distance between a risk envelope curve and the vehicle.
5. The method according to claim 1, wherein the obtaining, by the pre-trained driving style model, a base value of a driving style parameter of a driver of the vehicle, comprises: Acquiring real-time data of the vehicle in a current driving scene; extracting current driving characteristics of the driver based on the real-time data and a pre-constructed driving risk field model, wherein the current driving characteristics of the driver comprise at least one of driving risk characteristics, driving polite characteristics, driving efficiency characteristics and driving comfort characteristics; And inputting the current driving characteristics of the driver into the pre-trained driving style model to obtain the basic value of the driving style parameter of the driver.
6. The method of claim 5, wherein the training process of the driving style model comprises: acquiring a historical driving track data set of the driver; Determining driving characteristics of the driver based on the historical driving track data set of the driver and a pre-constructed driving risk field model, wherein the driving characteristics of the driver comprise at least one of driving risk characteristics, driving polite characteristics, driving efficiency characteristics and driving comfort characteristics; Training by using an inverse reinforcement learning algorithm based on the driving characteristics of the driver to obtain the driving style model.
7. The method of claim 6, wherein the determining driving characteristics of the driver based on the historical driving trajectory dataset of the driver, a pre-constructed driving risk field model, comprises: constructing a driving risk field of a neighboring vehicle, determining driving risk characteristics of the driver based on the driving risk field of the neighboring vehicle, and/or, Constructing a driving risk field of the vehicle, determining driving polite characteristics of the driver based on the driving risk field of the vehicle, and/or, Determining a driving efficiency characteristic of the driver based on speed limit information of a current lane of the vehicle and a speed of the host vehicle, and/or, And determining the driving comfort characteristics of the driver according to the lateral acceleration of the vehicle and the longitudinal acceleration of the vehicle.
8. The method according to any one of claims 1 to 7, wherein the obtaining a basic value of a driving style parameter of a driver of the vehicle comprises: starting to execute the step of acquiring the basic value of the driving style parameter of the driver of the vehicle if the intervention operation of the driver on the vehicle is monitored during the automatic driving of the vehicle; After the driving style parameter of the driver is determined based on the base value of the driving style parameter and the offset value of the driving style parameter, further comprising: And carrying out re-planning based on the driving style parameters, and controlling the vehicle to run according to a re-planned path.
9. An electronic device comprising a processor and a memory, wherein, The memory is used for storing a computer program; The processor being adapted to execute the computer program stored on the memory for implementing the method of any one of claims 1-8.
10. A vehicle according to claim 10, comprising an electronic device.
11. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-8.

Description

Driving style recognition method, driving style recognition device, vehicle and storage medium Technical Field The embodiment of the application relates to the technical field of intelligent driving, in particular to a driving style identification method, a driving style identification device, a vehicle and a storage medium. Background In an actual road traffic environment, driving behavior characteristics of different drivers have significant differences, and an automatic driving decision and control mode of a single behavior mode cannot be adapted to driving requirements of different drivers. In order to meet the individual driving requirements of different drivers, it is necessary to identify the driving style of the driver and study the individual characteristics of the driver. Disclosure of Invention The embodiment of the application provides a driving style identification method, a driving style identification device, a vehicle and a storage medium, and aims to solve the problem that an automatic driving decision and control mode of a single behavior mode in the related art cannot adapt to driving requirements of different drivers. In a first aspect, an embodiment of the application provides a driving style identification method, which comprises the steps of obtaining a basic value of a driving style parameter of a driver of a vehicle through a pre-trained driving style model, obtaining a driving parameter of a neighboring vehicle of the vehicle, determining an offset value of the driving style parameter of the driver based on the driving parameter of the neighboring vehicle of the vehicle, and determining the driving style parameter of the driver based on the basic value of the driving style parameter and the offset value of the driving style parameter. In a second aspect, an embodiment of the application provides a driving style identification device, which comprises a basic value acquisition module, a driving parameter acquisition module, an offset value acquisition module and a parameter determination module, wherein the basic value acquisition module is used for acquiring a basic value of a driving style parameter of a driver of a vehicle through a pre-trained driving style model, the driving parameter acquisition module is used for acquiring a driving parameter of a neighboring vehicle of the vehicle, the offset value acquisition module is used for determining an offset value of the driving style parameter of the driver based on the driving parameter of the neighboring vehicle of the vehicle, and the parameter determination module is used for determining the driving style parameter of the driver based on the basic value of the driving style parameter and the offset value of the driving style parameter. In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, where the memory is configured to store a computer program, and the processor is configured to execute the computer program stored in the memory, to implement the method described in the first aspect. In a fourth aspect, an embodiment of the present application provides a vehicle comprising an electronic device according to the third aspect. In a fifth aspect, an embodiment of the present application provides a computer readable storage medium, in which a computer program is stored, which when executed by a processor, implements the method according to the first aspect. Compared with the related art, the technical scheme provided by the embodiment of the application has at least the following technical effects: The driving style parameter of the driver is determined by acquiring the basic value of the driving style parameter of the driver and combining the driving parameters of the adjacent vehicles of the vehicle, and then the driving style parameter of the driver is determined based on the basic value and the offset value, and the offset value is determined based on the current driving parameters of the adjacent vehicles of the vehicle, so that the driving style and driving habit of the driver when the environment of the vehicle dynamically changes can be reflected, the influence of the driving environment on the driving style of the driver is fully considered, so that the finally determined driving style parameters have stronger consistency under different driving environments, and the actual driving style of the driver is more attached when the vehicle is controlled to run according to the determined driving style parameters, thereby meeting the personalized driving requirement of the driver. Drawings FIG. 1 is a flow chart of a driving style recognition method according to an embodiment of the present application; FIG. 2 is a flow chart of a driving style recognition method provided by another embodiment of the present application; FIG. 3 is a flow chart illustrating a process for determining a base value of a driving style parameter provided by one embodiment of the