Search

CN-122009209-A - Control method and device for vehicle, electronic equipment and storage medium

CN122009209ACN 122009209 ACN122009209 ACN 122009209ACN-122009209-A

Abstract

The application discloses a control method, a device, electronic equipment and a storage medium of a vehicle, wherein the vehicle is provided with a plurality of sensing equipment, and the method comprises the following steps: in the current running process of the vehicle, respectively acquiring sensing data from a plurality of sensing devices to obtain a plurality of sensing data, wherein the sensing data are used for displaying the environment of the vehicle; the method comprises the steps of generating environment description information of a vehicle based on a plurality of sensing data, wherein the environment description information is used for describing the environment through a preset information format, generating a predicted running track of the vehicle based on the environment description information and first sensing data in the plurality of sensing data, wherein the first sensing data is used for displaying the environment through images, the predicted running track is a running track of the vehicle in a future running process, the future running process is a running process after the current running process, and controlling the running of the vehicle according to the predicted running track in the environment. The application solves the technical problem of low control precision of the vehicle.

Inventors

  • ZHANG JINGJIA
  • LI PENGLONG
  • Huo Hongming

Assignees

  • 奇瑞汽车股份有限公司

Dates

Publication Date
20260512
Application Date
20260120

Claims (13)

  1. 1. A control method of a vehicle, characterized in that a plurality of sensing devices are disposed in the vehicle, the method comprising: In the current running process of the vehicle, respectively acquiring sensing data from a plurality of sensing devices to obtain a plurality of sensing data, wherein the sensing data are used for displaying the environment of the vehicle; Generating environment description information of the vehicle based on a plurality of the sensing data, wherein the environment description information is used for describing the environment through a preset information format; generating a predicted running track of the vehicle based on the environment description information and first sensing data in the plurality of sensing data, wherein the first sensing data is used for displaying the environment through images, the predicted running track is a running track of the vehicle in a future running process, and the future running process is a running process after the current running process; And under the environment, controlling the vehicle to run according to the predicted running track.
  2. 2. The method of claim 1, wherein the plurality of sensor data includes second sensor data and third sensor data, the first sensor data is sensor data from a first sensor device of the plurality of sensor devices, the second sensor data is sensor data from a second sensor device of the plurality of sensor devices, the third sensor data is sensor data from a third sensor device of the plurality of sensor devices, the type of the first sensor device, the type of the second sensor device, and the type of the third sensor device are different device types, and wherein generating the environmental description information of the vehicle based on the plurality of sensor data includes: performing image analysis on the first sensing data to obtain an image analysis result, wherein the image analysis result is used for representing different types of objects in the environment; clustering and fitting the second sensing data to obtain a fitting result, wherein the fitting result is used for representing the sizes of the objects of different types; Determining prediction state information of the different types of objects based on the third sensing data, wherein the prediction state information is used for representing the positions and the sizes of the different types of objects; And generating environment description information based on the image analysis result, the fitting result and the prediction state information.
  3. 3. The method of claim 2, wherein performing image analysis on the first sensed data to obtain an image analysis result comprises: Inputting the first sensing data into an image analyzer; extracting, in the image analyzer, first features of the different types of objects from the first sensed data; In the image analyzer, performing semantic segmentation on the first sensing data to obtain a semantic segmentation result, wherein the semantic segmentation result is used for representing semantic tags of the different types of objects; In the image analyzer, performing visual description on the first sensing data to obtain visual description results, wherein the visual description results are used for describing the states of the different types of objects under vision respectively; and determining the first feature, the semantic segmentation result and the visual description result as the image analysis result.
  4. 4. The method of claim 2, wherein clustering and fitting the second sensed data to obtain a fitting result comprises: Clustering the second sensing data to obtain clustering data of the objects of different types, wherein the clustering data is used for representing cluster categories to which the objects belong; And fitting the clustering data to obtain the fitting result.
  5. 5. The method of claim 2, wherein determining the predicted state information for the different type of object based on the third sensed data comprises: Extracting second features of the different types of objects from the third sensing data, and generating a feature map corresponding to the second features; and predicting the feature map by using a state prediction model to obtain the predicted state information, wherein the state prediction model is constructed based on a center point algorithm.
  6. 6. The method of claim 2, wherein generating environmental description information based on the image analysis result, the fitting result, and the predicted state information comprises: Performing time correction on the image analysis result and the fitting result according to the time stamp of the third sensing data; Converting the corrected image analysis result, the corrected fitting result and the prediction state information into a coordinate system where the vehicle is located to obtain a converted image analysis result, a converted fitting result and a converted prediction state information; and integrating the converted image analysis result, the converted fitting result and the converted prediction state information into the environment description information.
  7. 7. The method according to claim 1, wherein the method further comprises: acquiring input data from outside the vehicle, wherein the input data comprises meteorological data and scene data of the environment and driving data of the vehicle; Generating a predicted running track of the vehicle based on the environment description information and first sensing data in the plurality of sensing data comprises generating running track points of the vehicle in future running duration based on the input data, the environment description information and the first sensing data, fitting the running track points to obtain a fitted running track, and generating the predicted running track based on the fitted running track.
  8. 8. The method of claim 7, wherein generating the predicted travel track based on the fitted travel track comprises: generating a buffer area along the side edge of the fitting track; adjusting the fitting driving track in response to different types of objects in the environment being in the buffer area, and determining the adjusted fitting driving track as the predicted driving track; and determining the fitted driving track as the predicted driving track in response to the objects of different types in the environment not being in the buffer area.
  9. 9. The method of claim 1, wherein controlling the vehicle to travel according to the predicted travel trajectory in the environment comprises: Determining initial predicted running data corresponding to the predicted running track, wherein the initial predicted running data is used for representing an initial position and an initial speed of the vehicle in the future running process; and under the environment, controlling the vehicle to run according to the initial predicted running data.
  10. 10. The method according to claim 9, wherein the initial predicted travel data includes initial predicted position data for indicating an initial position at which the vehicle is in during the future travel and initial predicted speed data for indicating an initial speed at which the vehicle is in during the future travel, wherein controlling the travel of the vehicle in accordance with the initial predicted travel data under the environment includes: determining target predicted position data corresponding to the predicted running track, wherein the target predicted position data is used for representing a target position of the vehicle in the future running process, and the distance between the target position and the initial position is smaller than or equal to a preset distance; The initial predicted speed data is adjusted to obtain target predicted speed data, wherein the target predicted speed data is used for representing a target speed of the vehicle in the future driving process, and the speed difference between the target speed and the initial speed is smaller than or equal to a preset speed difference; and under the environment, controlling the vehicle to run according to the target predicted position data and the target predicted speed data.
  11. 11. A control apparatus of a vehicle, characterized in that a plurality of sensor devices are disposed in the vehicle, the apparatus comprising: The first acquisition unit is used for respectively acquiring sensing data from a plurality of sensing devices in the current running process of the vehicle to obtain a plurality of sensing data, wherein the sensing data are used for displaying the environment of the vehicle; A first generation unit configured to generate, based on a plurality of the sensor data, environment description information of the vehicle, wherein the environment description information is used to describe the environment in a preset information format; A second generation unit configured to generate a predicted travel track of the vehicle based on the environment description information and first sensor data of the plurality of sensor data, where the first sensor data is configured to display the environment through an image, the predicted travel track is a travel track of the vehicle in a future travel process, and the future travel process is a travel process after the current travel process; And the control unit is used for controlling the vehicle to run according to the predicted running track under the environment.
  12. 12. An electronic device, comprising: A memory storing an executable program; A processor for executing the program, wherein the program when run performs the method of any of claims 1 to 10.
  13. 13. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored executable program, wherein the executable program when run controls a device in which the storage medium is located to perform the method of any one of claims 1 to 10.

Description

Control method and device for vehicle, electronic equipment and storage medium Technical Field The embodiment of the application relates to the field of vehicles, in particular to a vehicle control method, a vehicle control device, electronic equipment and a storage medium. Background At present, in the existing multi-sensor fusion technology, a sensing module is often used as an independent module and is not coupled with the control of a vehicle, so that error propagation of data is easy to occur in a sudden dynamic scene, accurate data is difficult to provide for subsequent decision, and the problem of low control precision of the vehicle is caused. Aiming at the technical problem of low control precision of the vehicle, no effective solution is proposed at present. Disclosure of Invention The embodiment of the application provides a vehicle control method, a vehicle control device, electronic equipment and a storage medium, which are used for at least solving the technical problem of low control precision of a vehicle. According to one aspect of the embodiment of the application, a control method of a vehicle is provided, the vehicle is provided with a plurality of sensing devices, the method comprises the steps of respectively acquiring sensing data from the plurality of sensing devices in the current running process of the vehicle to obtain the plurality of sensing data, wherein the sensing data are used for showing the environment of the vehicle, generating environment description information of the vehicle based on the plurality of sensing data, wherein the environment description information is used for describing the environment through a preset information format, and generating a predicted running track of the vehicle based on the environment description information and first sensing data in the plurality of sensing data, wherein the first sensing data are used for showing the environment through images, the predicted running track is the running track of the vehicle in the future running process, the future running process is the running process after the current running process, and controlling the running of the vehicle according to the predicted running track in the environment. Further, the plurality of sensing data comprises second sensing data and third sensing data, the first sensing data is sensing data from a first sensing device in the plurality of sensing devices, the second sensing data is sensing data from a second sensing device in the plurality of sensing devices, the third sensing data is sensing data from a third sensing device in the plurality of sensing devices, the type of the first sensing device, the type of the second sensing device and the type of the third sensing device are different device types, wherein environmental description information of the vehicle is generated based on the plurality of sensing data, the method comprises the steps of performing image analysis on the first sensing data to obtain an image analysis result, wherein the image analysis result is used for representing different types of objects in the environment, clustering and fitting the second sensing data to obtain a fitting result, wherein the fitting result is used for representing sizes of the different types of objects, the prediction state information of the different types of objects is determined based on the third sensing data, and the prediction state information is used for representing positions and sizes of the different types of the objects. Further, image analysis is carried out on the first sensing data to obtain an image analysis result, the image analysis result comprises the steps of inputting the first sensing data into an image analyzer, extracting first characteristics of different types of objects from the first sensing data in the image analyzer, carrying out semantic segmentation on the first sensing data in the image analyzer to obtain a semantic segmentation result, wherein the semantic segmentation result is used for representing semantic tags of the different types of objects, carrying out visual description on the first sensing data in the image analyzer to obtain a visual description result, wherein the visual description result is used for describing states of the different types of objects under the vision respectively, and determining the first characteristics, the semantic segmentation result and the visual description result as the image analysis result. Further, clustering and fitting are carried out on the second sensing data to obtain a fitting result, wherein the clustering and fitting are carried out on the second sensing data to obtain clustering data of different types of objects, the clustering data are used for representing cluster types of the objects, and the fitting is carried out on the clustering data to obtain the fitting result. Further, based on the third sensing data, the prediction state information of the different types of objects is determi