CN-122009181-A - Vehicle control method, apparatus, device, storage medium, and program product

CN122009181ACN 122009181 ACN122009181 ACN 122009181ACN-122009181-A

Abstract

The application relates to a vehicle control method, a device, equipment, a storage medium and a program product, which can be used in the technical field of vehicles. The method comprises the steps of obtaining current data of a vehicle, wherein the current data comprise current driving operation data, current vehicle state data and current environment sensing data, inputting the current data into a pre-trained overtaking intention recognition model to perform overtaking intention recognition processing to obtain overtaking intention recognition results corresponding to the vehicle, determining a target power mode of the vehicle according to the overtaking intention recognition results, and controlling the current power mode of the vehicle according to the target power mode. By adopting the method, the safety of the power mode control of the vehicle can be improved.

Inventors

Lei Xiujie
WEN QIAN
JIE LIZHU
CHENG XU
LI XINQI

Assignees

赛力斯汽车有限公司

Dates

Publication Date: 20260512
Application Date: 20260316

Claims (11)

1. A vehicle control method, characterized in that the method comprises: acquiring current data of a vehicle, wherein the current data comprises current driving operation data, current vehicle state data and current environment perception data; Inputting the current data into a pre-trained overtaking intention recognition model to perform overtaking intention recognition processing, so as to obtain overtaking intention recognition results corresponding to the vehicle; Determining a target power mode of the vehicle according to the overtaking intention recognition result; And according to the target power mode, performing control processing on the current power mode of the vehicle.
2. The method of claim 1, wherein the overtaking intent recognition result includes an overtaking intent state, an overtaking progress state, or an overtaking end state; The determining the target power mode of the vehicle according to the overtaking intention recognition result comprises the following steps: determining that the target power mode is a preset motion mode of the vehicle under the condition that the overtaking intention recognition result indicates the overtaking intention state; Determining that the target power mode is the current power mode of the vehicle under the condition that the overtaking intention recognition result is the overtaking running state; and determining the target power mode as the initial power mode of the vehicle under the condition that the overtaking intention recognition result is the overtaking ending state and the real-time driving operation data of the vehicle is detected to meet the preset stable condition in the preset time.
3. The method of claim 1, wherein the pre-trained overtaking intent recognition model is trained by: The method comprises the steps of acquiring historical data of the vehicle, wherein the historical data comprises historical driving operation data, historical vehicle state data and historical environment perception data of the vehicle; determining a historical overtaking event and a historical non-overtaking event of the vehicle according to the historical data; generating positive sample data of the vehicle according to the historical overtaking event, and generating negative sample data of the vehicle according to the historical non-overtaking event; And performing iterative training on the overtaking intention recognition model to be trained according to the positive sample data and the negative sample data to obtain the overtaking intention recognition model trained in advance.
4. The method of claim 3, wherein the generating positive sample data for the vehicle from the historical cut-in event comprises: Identifying the starting time and the ending time of the historical overtaking event; Determining a time period of the overtaking intention state, a time period of the overtaking progress state and a time period of the overtaking ending state of the vehicle according to the starting time and the ending time; And according to the time period of the overtaking intention state, the time period of the overtaking running state and the time period of the overtaking ending state, carrying out corresponding extraction processing on the historical data to obtain the positive sample data.
5. The method of claim 4, wherein identifying the starting time of the historical cut-in event comprises: The method comprises the steps of taking a moment corresponding to a first condition of the vehicle as the starting moment, wherein the first condition is used for representing the situation that the duration of a turn signal on state of the vehicle exceeds a preset duration threshold value, the opening of an accelerator pedal of the vehicle exceeds a preset opening threshold value and the space state of an adjacent lane of the vehicle is available in the historical overtaking event; or the moment corresponding to the second condition of the vehicle is used as the starting moment, wherein the second condition is used for representing the situation that the steering wheel angle of the vehicle exceeds a preset steering angle threshold value, the space state of the adjacent lane of the vehicle is an available state and the change rate of the accelerator pedal opening of the vehicle exceeds a preset change rate threshold value in the history overtaking event.
6. The method of claim 4, wherein identifying the end time of the historical cut-in event comprises: identifying the corresponding moment when the steering wheel of the vehicle in the historical overtaking event meets a preset state as the ending moment; Or identifying the corresponding moment when the turn signal of the vehicle in the history overtaking event enters the off state as the ending moment; or identifying the moment corresponding to the moment when the overtaking operation of the vehicle is completed in the historical overtaking event and the opening of the accelerator pedal of the vehicle is smaller than a preset opening threshold value as the ending moment; Or identifying the moment corresponding to the moment when the vehicle finishes lane change operation in the history overtaking event and the stable running time of the vehicle on the central line of the target lane exceeds a preset stable time threshold value as the ending moment.
7. The method according to any one of claims 1 to 6, wherein the step of inputting the current data into a pre-trained overtaking intention recognition model to perform overtaking intention recognition processing to obtain overtaking intention recognition results corresponding to the vehicle includes: dividing the current data according to a preset time window to obtain time sequence data in the preset time window; and inputting the time sequence data into the pre-trained overtaking intention recognition model to perform overtaking intention recognition processing, so as to obtain the overtaking intention recognition result.
8. A vehicle control apparatus, characterized in that the apparatus comprises: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring current data of a vehicle, and the current data comprises current driving operation data, current vehicle state data and current environment perception data; the data input module is used for inputting the current data into a pre-trained overtaking intention recognition model to perform overtaking intention recognition processing to obtain overtaking intention recognition results corresponding to the vehicle; The mode determining module is used for determining a target power mode of the vehicle according to the overtaking intention recognition result; And the mode control module is used for controlling the current power mode of the vehicle according to the target power mode.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
11. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.

Description

Vehicle control method, apparatus, device, storage medium, and program product Technical Field The present application relates to the field of vehicle technologies, and in particular, to a vehicle control method, apparatus, device, storage medium, and program product. Background In an actual driving scenario, a cut-in is a common but risky driving behavior, and a driver often needs a stronger power response during the cut-in to ensure that the cut-in action is completed safely and quickly. In the related art, control of a power mode of a vehicle mainly depends on manual selection by a driver. However, in a scene where instantaneous power boost is required such as overtaking, manual selection by the driver may affect driving safety, resulting in lower safety of power mode control of the vehicle. Disclosure of Invention In view of the foregoing, it is desirable to provide a vehicle control method, apparatus, computer device, computer-readable storage medium, and computer program product that are capable of improving the safety of power mode control of a vehicle. In a first aspect, the present application provides a vehicle control method. The method comprises the following steps: acquiring current data of a vehicle, wherein the current data comprises current driving operation data, current vehicle state data and current environment perception data; Inputting the current data into a pre-trained overtaking intention recognition model to perform overtaking intention recognition processing, so as to obtain overtaking intention recognition results corresponding to the vehicle; Determining a target power mode of the vehicle according to the overtaking intention recognition result; And according to the target power mode, performing control processing on the current power mode of the vehicle. The method has the advantages that the method is beneficial to providing sufficient data support for overtaking intention recognition by acquiring the current data of the vehicle including the current driving operation data, the current vehicle state data and the current environment sensing data, is beneficial to predicting overtaking intention of a driver before overtaking actually occurs by inputting the current data into a pre-trained overtaking intention recognition model to perform overtaking intention recognition processing, is beneficial to realizing early recognition of overtaking intention, is beneficial to timely determining a switched power mode when overtaking intention is recognized by determining a target power mode of the vehicle according to overtaking intention recognition results, is beneficial to completing switching of the power mode before overtaking is performed by controlling the current power mode according to the target power mode, and is beneficial to improving safety of power mode control of the vehicle, avoiding insufficient power response caused by power switching delay and improving power response speed and overtaking efficiency of the vehicle in the overtaking process. In an optional embodiment of the first aspect, the overtaking intention recognition result includes an overtaking intention state, an overtaking progress state, or an overtaking end state; The determining the target power mode of the vehicle according to the overtaking intention recognition result comprises the following steps: determining that the target power mode is a preset motion mode of the vehicle under the condition that the overtaking intention recognition result indicates the overtaking intention state; Determining that the target power mode is the current power mode of the vehicle under the condition that the overtaking intention recognition result is the overtaking running state; and determining the target power mode as the initial power mode of the vehicle under the condition that the overtaking intention recognition result is the overtaking ending state and the real-time driving operation data of the vehicle is detected to meet the preset stable condition in the preset time. The method has the advantages that differentiated power mode control is facilitated for different stages of an overtaking process by distinguishing three different states of an overtaking intention state, an overtaking running state and an overtaking ending state, when the overtaking intention recognition result shows the overtaking intention state, the target power mode is determined to be the preset motion mode, the method is beneficial to completing early switching of the power mode before a driver does not execute overtaking operation, ensuring that the driver can obtain sufficient power output when the overtaking operation starts, improving safety and efficiency of overtaking, keeping the current power mode unchanged in the overtaking running state, facilitating maintenance of power output stability in the overtaking process, and determining that the target power mode is the initial power mode of the vehicle when the overtaking intention recogn