Method and apparatus of controlling driverless vehicle and electronic device

Patent metadata

Field	Value
Publication number	US-11891085-B2
Application number	US-202117453743-A
Country	US
Kind code	B2
Filing date	Nov 5, 2021
Priority date	Dec 15, 2020
Publication date	Feb 6, 2024
Grant date	Feb 6, 2024

Abstract

A method and an apparatus of controlling a driverless vehicle and an electronic device are provided, and relates to the field of artificial intelligence technologies, such as computer vision and self-driving. The method includes: in a case that a stop instruction is received or a driverless vehicle arrives at a preset position, acquiring a first road surface image captured by a camera of the driverless vehicle that is on a same side of a door of the driverless vehicle; acquiring, based on the first road surface image, a target road surface state of road surface on one or two sides of the driverless vehicle that are provided with a door; in a case that the target road surface state is a first road surface state, controlling the driverless vehicle to stop.

First claim

What is claimed is:

1. A method of controlling a driverless vehicle, comprising:
in a case that a stop instruction is received or the driverless vehicle arrives at a preset position, acquiring a first road surface image captured by a camera of the driverless vehicle that is on a same side of a door of the driverless vehicle;
acquiring, based on the first road surface image, a target road surface state of a road surface on one or two sides of the driverless vehicle that are provided with the door;
in a case that the target road surface state is a first road surface state, controlling the driverless vehicle to stop;
wherein, after the acquiring, based on the first road surface image, the target road surface state of the road surface on one or two sides of the driverless vehicle that are provided with the door, the method further comprises:
in a case that the target road surface state is a second road surface state, outputting a first prompt message, wherein the first prompt message is configured to prompt that a current road surface is not suitable for stop;
in a case that a second input is received from a user, controlling the driverless vehicle to keep moving;
in a case that a current time reaches a first time, controlling the camera to capture a second road surface image, updating the first road surface image with the second road surface image, and returning to the step of determining, based on the first road surface image, the target road surface state of the road surface on one or two sides of the driverless vehicle that are provided with the door, until the driverless vehicle stops;
wherein, a time difference between the first time and a time when the second input is received is less than a preset time length;
wherein the method further comprises:
when the number of times the second input is received is less than a preset number of times, controlling the driverless vehicle to keep moving;
when the number of times the second input is received is greater than or equal to the preset number of times, controlling the driverless vehicle to stop.

2. The method according to claim 1 , wherein the camera is mounted on a rear view mirror of the driverless vehicle and is configured to capture a road surface image of road the surface on a side of the driverless vehicle.

3. The method according to claim 1 , wherein the acquiring, based on the first road surface image, the target road surface state of the road surface on one or two sides of the driverless vehicle that are provided with the door comprises:
performing feature extraction on the first road surface image to obtain first feature data;
determining the target road surface state by matching the first feature data with a preset feature database stored in the driverless vehicle.

4. The method according to claim 3 , wherein the determining the target road surface state by matching the first feature data with the preset feature database stored in the driverless vehicle comprises:
in a case that the preset feature database does not comprise a target feature data matching the first feature data, determining that the target road surface state is a first road surface state; or,
in a case that the preset feature database comprises a target feature data matching the first feature data, determining that the target road surface state is a second road surface state.

5. The method according to claim 1 , wherein the acquiring, based on the first road surface image, the target road surface state of the road surface on one or two sides of the driverless vehicle that are provided with the door comprises:
transmitting the first road surface image to a cloud server;
receiving the target road surface state transmitted by the cloud server and obtained from identification performed by the cloud server on the first road surface image by using a road surface state identification model, wherein the target road surface state comprises a first road surface state or a second road surface state.

6. The method according to claim 1 , wherein, after the outputting the first prompt message, the method further comprises:
in a case that a first input is received from a user, controlling the driverless vehicle to stop.

7. A non-transitory computer readable storage medium, storing therein a computer instruction, wherein the computer instruction is configured to be executed by a computer, to implement the method according to claim 1 .

8. An apparatus of controlling a driverless vehicle, comprising:
at least one processor; and
a storage communicatively connected to the at least one processor,
wherein the storage stores therein an instruction configured to be executed by the at least one processor, and the at least one processor is configured to execute the instruction to:
in a case that a stop instruction is received or the driverless vehicle arrives at a preset position, acquire a first road surface image captured by a camera of the driverless vehicle that is on a same side of a door of the driverless vehicle;
acquire, based on the first road surface image, a target road surface state of a road surface on one or two sides of the driverless vehicle that are provided with the door;
in a case that the target road surface state is a first road surface state, control the driverless vehicle to stop;
wherein the at least one processor is configured to execute the instruction to:
after the acquiring, based on the first road surface image, the target road surface state of the road surface on one or two sides of the driverless vehicle that are provided with the door,
in a case that the target road surface state is a second road surface state, outputting a first prompt message, wherein the first prompt message is configured to prompt that a current road surface is not suitable for stop;
in a case that a second input is received from a user, controlling the driverless vehicle to keep moving;
in a case that a current time reaches a first time, controlling the camera to capture a second road surface image, updating the first road surface image with the second road surface image, and returning to the step of determining, based on the first road surface image, the target road surface state of the road surface on one or two sides of the driverless vehicle that are provided with the door, until the driverless vehicle stops;
wherein, a time difference between the first time and a time when the second input is received is less than a preset time length;
wherein the at least one processor is configured to execute the instruction to:
when the number of times the second input is received is less than a preset number of times, controlling the driverless vehicle to keep moving;
when the number of times the second input is received is greater than or equal to the preset number of times, controlling the driverless vehicle to stop.

9. The apparatus according to claim 8 , wherein the camera is mounted on a rear view mirror of the driverless vehicle and is configured to capture a road surface image of road surface on a side of the driverless vehicle.

10. The apparatus according to claim 8 , wherein the at least one processor is configured to execute the instruction to:
perform feature extraction on the first road surface image to obtain first feature data;
determine the target road surface state by matching the first feature data with a preset feature database stored in the driverless vehicle.

11. The apparatus according to claim 10 , wherein the at least one processor is configured to execute the instruction to:
in a case that the preset feature database does not comprise a target feature data matching the first feature data, determine that the target road surface state is

Assignees

• Apollo Intelligent Connectivity Beijing Technology Co Ltd

Inventors

• Luo Xiang

Classifications

• B60W2552/00

  Input parameters relating to infrastructure · CPC title

• B60W60/00253

  Taxi operations · CPC title

• B60W30/06 Primary

  Automatic manoeuvring for parking · CPC title

• B60W60/001 Primary

  Planning or execution of driving tasks · CPC title

• B60R1/12

  Mirror assemblies combined with other articles, e.g. clocks · CPC title