Bend driving control method for autonomous vehicle, device, and medium

Patent metadata

Field	Value
Publication number	US-11767029-B2
Application number	US-202017032090-A
Country	US
Kind code	B2
Filing date	Sep 25, 2020
Priority date	Feb 19, 2020
Publication date	Sep 26, 2023
Grant date	Sep 26, 2023

Abstract

Embodiments of the present disclosure provide a bend driving control method for an autonomous vehicle, a device and a storage medium, and relate to a field of perception and autonomous driving technologies. The method includes: obtaining an occupancy width of an autonomous vehicle on a target bend when the autonomous vehicle drives on the target bend; detecting location information of an obstacle on the target bend; and controlling a driving route of the autonomous vehicle on the target bend based on the occupancy width and the location information of the obstacle.

First claim

What is claimed is:

1. A bend driving control method for an autonomous vehicle, comprising:
obtaining a size of the autonomous vehicle and a curvature of a target bend; and
determining, based on the size of the autonomous vehicle and the curvature of the target bend, an occupancy width of the autonomous vehicle on the target bend when the autonomous vehicle drives on the target bend;
detecting location information of an obstacle on the target bend; and
controlling a driving route of the autonomous vehicle on the target bend based on the occupancy width and the location information of the obstacle;
wherein obtaining the curvature of the target bend comprises:
selecting any point on the target bend as a projection point of a corner point of the autonomous vehicle on the target bend;
initializing the curvature of the target bend;
determining a center position of the autonomous vehicle, tangent direction corresponding to a driving direction of the autonomous vehicle at the target location, and the location of an intersection of an edge at a corner side of the autonomous vehicle and the target bend based on a position of the target point, the curvature of the target bend at the target location and the size of the autonomous vehicle;
determining an angle between the tangent direction and a line connecting the center position and the intersection; and
updating the curvature of the target bend at the target location with the angle, and repeating the calculation of the center position, the tangent direction and the location of the intersection until a preset iteration condition is satisfied.

2. The method according to claim 1 , wherein controlling the driving route of the autonomous vehicle on the target bend based on the occupancy width and the location information of the obstacle comprises:
determining ab obstacle avoidance distance of the autonomous vehicle driving on the target bend according to the occupancy width; and
controlling the driving route of the autonomous vehicle on the target bend based on the location information of the obstacle, so that a lateral distance between the autonomous vehicle and the obstacle exceeds the obstacle avoidance distance.

3. The method according to claim 1 , wherein determining the occupancy width based on the size of the autonomous vehicle and the curvature of the target bend comprises:
determining an occupancy width of the autonomous vehicle at a target point when the autonomous vehicle travels to a target location based on a curvature of the target bend at the target location and the size of the autonomous vehicle,
wherein, the target point is a projection point of a corner point of the autonomous vehicle on the target bend when the autonomous vehicle travels to the target location of the target bend.

4. The method according to claim 3 , wherein the corner point comprises a front corner point and a rear corner point; and
determining the occupancy width of the autonomous vehicle at the target point when the autonomous vehicle travels to the target location based on the curvature of the target bend at the target location and the size of the autonomous vehicle, comprises:
in response to determining that the target point is a projection point of the front corner point on the target bend, determining a first width of occupancy of the autonomous vehicle at the target point when the autonomous vehicle travels to the target location based on the curvature of the target bend at the target location and the size of the autonomous vehicle;
in response to determining that the target point is a projection point of the rear corner point on the target bend, determining a second width of occupancy of the autonomous vehicle at the target point when the autonomous vehicle travels to the target location based on the curvature of the target bend at the target location and the size of the autonomous vehicle; and
determining the occupancy width of the autonomous vehicle at the target point when the autonomous vehicle travels to the target location based on a larger one of the first width and the second width.

5. The method according to claim 3 , wherein determining the occupancy width of the autonomous vehicle at the target point when the autonomous vehicle travels to the target location based on the curvature of the target bend at the target location and the size of the autonomous vehicle, comprises:
obtaining a curve direction of the target bend in a driving direction at the target location;
in response to determine that the curve direction is to the left, determining a right-side occupancy width of the autonomous vehicle at the target point when the autonomous vehicle travels to the target location based on the curvature of the target bend at the target location and the size of the autonomous vehicle, and determining a left-side occupancy width of the autonomous vehicle at the target point when the autonomous vehicle travels to the target location based on a half of a width of the autonomous vehicle; and
in response to determine that the curve direction is to the right, determining a left-side occupancy width of the autonomous vehicle at the target point when the autonomous vehicle travels to the target location based on the curvature of the target bend at the target location and the size of the autonomous vehicle, and determining a right-side occupancy width of the autonomous vehicle at the target point when the autonomous vehicle travels to the target location based on a half of the width of the autonomous vehicle.

6. The method according to claim 5 , wherein obtaining the curve direction of the target bend in the driving direction at the target location comprises:
obtaining a first tangent direction at the target location and a second tangent direction at the target point; and
determining the curve direction according to an angle relation between the first tangent direction and the second tangent direction.

7. The method according to claim 1 , wherein obtaining the size of the autonomous vehicle comprises:
obtaining a maximum vehicle width and a maximum vehicle length of the autonomous vehicle; and
determining a size of a circumscribed rectangle of the autonomous vehicle as the size of the autonomous vehicle according to the maximum vehicle width and the maximum vehicle length.

8. An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor; wherein,
the memory having instructions executable by the at least one processor stored thereon, and when the instructions are executed by the at least one processor, the at least one processor is caused to execute a bend driving control method for an autonomous vehicle, the method comprising:
obtaining a size of the autonomous vehicle and a curvature of a target bend; and
determining, based on the size of the autonomous vehicle and the curvature of the target bend, an occupancy width of the autonomous vehicle on the target bend when the autonomous vehicle drives on the target bend;
detecting location information of an obstacle on the target bend; and
controlling a driving route of the autonomous vehicle on the target bend based on the occupancy width and the location information of the obstacle;
wherein obtaining the curvature of the target bend comprises:
selecting any point on the target bend as a projection point of a corner point of the autonomous vehicle on the target bend;
initializing the curvature of the target bend;
determining a center position of the autonomous vehicle, a tangent direction corresponding to a driving direction of the autonomous vehicle at the target location, and location of an intersection of an edge at a corner side of the autonomous vehicle and the target bend based

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Chen Zhiyuan
• Fu Xiaoxin
• Ma Lin
• Li Xujian
• Zhu Zhenguang

Classifications

• B60W2554/4041

  Position · CPC title

• B60W2552/30

  Road curve radius · CPC title

• B60W2530/201

  Dimensions of vehicle · CPC title

• B60W60/0011 Primary

  involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles · CPC title

• B60W30/09

  Taking automatic action to avoid collision, e.g. braking and steering · CPC title