Method for detecting closest in-path object (CIPO) for autonomous driving

Patent metadata

Field	Value
Publication number	US-10915766-B2
Application number	US-201916457719-A
Country	US
Kind code	B2
Filing date	Jun 28, 2019
Priority date	Jun 28, 2019
Publication date	Feb 9, 2021
Grant date	Feb 9, 2021

Abstract

In one embodiment, in addition to detecting or recognizing an actual lane, a virtual lane is determined based on the current state or motion prediction of an ADV. A virtual lane may or may not be identical or similar to the actual lane. A virtual lane may represent the likely movement of the ADV in a next time period given the current speed and heading direction of the vehicle. If an object is detected that may cross a lane line of the virtual lane and is a closest object to the ADV, the object is considered as a CIPO, and an emergency operation may be activated. That is, even though an object may not be in the path of an actual lane, if the object is in the path of a virtual lane of an ADV, the object may be considered as a CIPO and subject to a special operation.

First claim

What is claimed is:

1. A computer-implemented method for detecting closest in-path objects for autonomous driving, the method comprising:
perceiving a driving environment surrounding an autonomous driving vehicle (ADV) based on sensor data obtained from a plurality of sensors mounted on the ADV, including detecting one or more objects;
determining an operating state of the ADV including a speed and a heading direction of the ADV;
generating a virtual lane based on the operating state of the ADV, the virtual lane representing a path along which the ADV likely will move within a predetermined time period;
determining whether at least a portion of a first object of the detected objects falls within the virtual lane; and
classifying the first object as a closest in-path object (CIPO), in response to determining that at least a portion of the first object falls within the virtual lane.

2. The method of claim 1 , further comprising activating an emergency operation to control the ADV to avoid a collision with the first object, in response to determining that the first object is a CIPO.

3. The method of claim 1 , wherein the virtual lane is generated without using map data of a map associated with a road the ADV is currently located and without being based on an actual lane of the road recognized based on the sensor data.

4. The method of claim 1 , wherein generating a virtual lane comprises:
determining a virtual lane length based on the speed of the ADV and the predetermined time period;
determining a curvature of the virtual lane based on the heading direction of the ADV; and
determining a virtual lane width of the virtual lane based on a physical dimension of the ADV.

5. The method of claim 4 , wherein the virtual lane width is determined further based on at least one of a type of road or a traffic regulation.

6. The method of claim 1 , further comprising:
detecting a second object within an actual lane recognized based on the perceived driving environment that the ADV likely collides within the predetermined time period based on the operating state of the ADV;
measuring a first distance between the ADV and the first object and a second distance between the ADV and the second object; and
designating the first object as the CIPO if the first distance is shorter than the second distance.

7. The method of claim 1 , wherein generating the virtual lane comprises determining a first lane line and a second lane line to define a shape and a lane width of the virtual lane.

8. The method of claim 7 , wherein the first lane line is determined based on at least one of map data or a lane mark recognized based on perceived driving environment, and wherein the second lane line is derived from the first lane line in view of a set of rules.

9. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
perceiving a driving environment surrounding an autonomous driving vehicle (ADV) based on sensor data obtained from a plurality of sensors mounted on the ADV, including detecting one or more objects;
determining an operating state of the ADV including a speed and a heading direction of the ADV;
generating a virtual lane based on the operating state of the ADV, the virtual lane representing a path along which the ADV likely will move within a predetermined time period;
determining whether at least a portion of a first object of the detected objects falls within the virtual lane; and
classifying the first object as a closest in-path object (CIPO), in response to determining that at least a portion of the first object falls within the virtual lane.

10. The machine-readable medium of claim 9 , wherein the operations further comprise activating an emergency operation to control the ADV to avoid a collision with the first object, in response to determining that the first object is a CIPO.

11. The machine-readable medium of claim 9 , wherein the virtual lane is generated without using map data of a map associated with a road the ADV is currently located and without being based on an actual lane of the road recognized based on the sensor data.

12. The machine-readable medium of claim 9 , wherein generating a virtual lane comprises:
determining a virtual lane length based on the speed of the ADV and the predetermined time period;
determining a curvature of the virtual lane based on the heading direction of the ADV; and
determining a virtual lane width of the virtual lane based on a physical dimension of the ADV.

13. The machine-readable medium of claim 12 , wherein the virtual lane width is determined further based on at least one of a type of road or a traffic regulation.

14. The machine-readable medium of claim 9 , wherein the operations further comprise:
detecting a second object within an actual lane recognized based on the perceived driving environment that the ADV likely collides within the predetermined time period based on the operating state of the ADV;
measuring a first distance between the ADV and the first object and a second distance between the ADV and the second object; and
designating the first object as the CIPO if the first distance is shorter than the second distance.

15. The machine-readable medium of claim 9 , wherein generating the virtual lane comprises determining a first lane line and a second lane line to define a shape and a lane width of the virtual lane.

16. The machine-readable medium of claim 15 , wherein the first lane line is determined based on at least one of map data or a lane mark recognized based on perceived driving environment, and wherein the second lane line is derived from the first lane line in view of a set of rules.

17. A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including
perceiving a driving environment surrounding an autonomous driving vehicle (ADV) based on sensor data obtained from a plurality of sensors mounted on the ADV, including detecting one or more objects,
determining an operating state of the ADV including a speed and a heading direction of the ADV,
generating a virtual lane based on the operating state of the ADV, the virtual lane representing a path along which the ADV likely will move within a predetermined time period,
determining whether at least a portion of a first object of the detected objects falls within the virtual lane, and
classifying the first object as a closest in-path object (CIPO), in response to determining that at least a portion of the first object falls within the virtual lane.

18. The system of claim 17 , wherein the operations further comprise activating an emergency operation to control the ADV to avoid a collision with the first object, in response to determining that the first object is a CIPO.

19. The system of claim 17 , wherein the virtual lane is generated without using map data of a map associated with a road the ADV is currently located and without being based on an actual lane of the road recognized based on the sensor data.

20. The system of claim 17 , wherein generating a virtual lane comprises:
determining a virtual lane length based on the speed of the ADV and the predetermined time period;
determining a curvature of the virtual lane based on the heading direction of the ADV; and
determining a virtual lane width of the virtual

Assignees

• Baidu Usa Llc

Inventors

• Choe Tae Eun
• Guo Yuliang
• Chen Guang
• Zhang Weide
• Tsoi Ka Wai

Classifications

• G06T11/23

  using straight lines or curves · CPC title

• G06V20/588

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title

• G06V20/58 Primary

  Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads · CPC title

• G06V20/56

  exterior to a vehicle by using sensors mounted on the vehicle · CPC title

• G06T11/00

  Two-dimensional [2D] image generation · CPC title