Method and device for controlling vehicle, device, and storage medium
View Patent ↗The present disclosure provides a method and a device for controlling a vehicle, a device and a storage medium, and relates to the field of unmanned vehicle technologies. The method includes: acquiring a vehicle environment image by an image acquirer during traveling of the vehicle; extracting a static environment image included in the vehicle environment image; obtaining a planned vehicle traveling trajectory by taking the static environment image as an input of a trajectory planning model; and controlling the vehicle to travel according to the planned vehicle traveling trajectory.
1. A method for controlling a vehicle, comprising:
acquiring a vehicle environment image of the vehicle by an image acquirer during traveling of the vehicle;
extracting a static environment image comprised in the vehicle environment image;
obtaining a planned vehicle traveling trajectory by taking the static environment image as an input of a trajectory planning model, wherein the trajectory planning model is obtained by training a neural network model with taking a historical static environment image as an input of the neural network model, and taking a historical vehicle traveling trajectory associated with the historical static environment image as an output of the neural network model; and
controlling the vehicle to travel according to the planned vehicle traveling trajectory.
2. The method according to claim 1 , wherein extracting the static environment image comprised in the vehicle environment image comprises:
recognizing a dynamic object comprised in the vehicle environment image; and
filtering the dynamic object in the vehicle environment image to obtain the static environment image.
3. The method according to claim 1 , wherein extracting the static environment image comprised in the vehicle environment image comprises:
determining a traveling environment of the vehicle according to the vehicle environment image; and
when the traveling environment is an outdoor traveling environment, extracting a road surface image in the vehicle environment image.
4. The method according to claim 3 , wherein after determining the traveling environment of the vehicle according to the vehicle environment image, the method further comprises:
when the traveling environment is an indoor traveling environment, extracting the road surface image and a ceiling image in the vehicle environment image.
5. A device for controlling a vehicle, comprising:
one or more processors;
a storage device, configured to store one or more programs;
wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to:
acquire a vehicle environment image by an image acquirer during traveling of the vehicle;
extract a static environment image comprised in the vehicle environment image;
obtain a planned vehicle traveling trajectory by taking the static environment image as an input of a trajectory planning model, wherein the trajectory planning model is obtained by training a neural network model with taking a historical static environment image as an input of the neural network model, and taking a historical vehicle traveling trajectory associated with the historical static environment image as an output of the neural network model; and
control the vehicle to travel according to the planned vehicle traveling trajectory.
6. The device according to claim 5 , wherein the one or more processors are configured to:
recognize a dynamic object comprised in the vehicle environment image; and
filter the dynamic object in the vehicle environment image to obtain the static environment image.
7. The device according to claim 5 , wherein the one or more processors are configured to:
determine a traveling environment of the vehicle according to the vehicle environment image; and
extract a road surface image in the vehicle environment image when the traveling environment is an outdoor traveling environment.
8. The device according to claim 7 , wherein the one or more processors are configured to:
extract the road surface image and a ceiling image in the vehicle environment image when the traveling environment is an indoor traveling environment.
9. A non-transitory computer readable storage medium having stored thereon a computer program that, when executed by a processor, causes a method for controlling a vehicle to be implemented, the method comprising:
acquiring a vehicle environment image of the vehicle by an image acquirer during traveling of the vehicle;
extracting a static environment image comprised in the vehicle environment image;
obtaining a planned vehicle traveling trajectory by taking the static environment image as an input of a trajectory planning model, wherein the trajectory planning model is obtained by training a neural network model with taking a historical static environment image as an input of the neural network model, and taking a historical vehicle traveling trajectory associated with the historical static environment image as an output of the neural network model; and
controlling the vehicle to travel according to the planned vehicle traveling trajectory.
10. The non-transitory computer readable storage medium according to claim 9 , wherein extracting the static environment image comprised in the vehicle environment image comprises:
recognizing a dynamic object comprised in the vehicle environment image; and
filtering the dynamic object in the vehicle environment image to obtain the static environment image.
11. The non-transitory computer readable storage medium according to claim 9 , wherein extracting the static environment image comprised in the vehicle environment image comprises:
determining a traveling environment of the vehicle according to the vehicle environment image; and
when the traveling environment is an outdoor traveling environment, extracting a road surface image in the vehicle environment image.
12. The non-transitory computer readable storage medium according to claim 11 , wherein after determining the traveling environment of the vehicle according to the vehicle environment image, the method further comprises:
when the traveling environment is an indoor traveling environment, extracting the road surface image and a ceiling image in the vehicle environment image.