Nested scenarios in planning for autonomous driving vehicles

Patent metadata

Field	Value
Publication number	US-11673576-B2
Application number	US-202016827510-A
Country	US
Kind code	B2
Filing date	Mar 23, 2020
Priority date	Mar 23, 2020
Publication date	Jun 13, 2023
Grant date	Jun 13, 2023

Abstract

In one embodiment, an ADV is routed by executing a first driving scenario that is active. The first driving scenario is one of a plurality of driving scenario types, each driving scenario type being associated with one or more stages to be executed while a corresponding driving scenario type is active. Based on an environmental condition around the ADV, a second driving scenario is set as active. The ADV is routed by executing the second driving scenario. When the second driving scenario exits, execution of the first driving scenario resumes at the one or more stages of the first driving scenario that remains to be executed.

First claim

What is claimed is:

1. A method for controlling an autonomous driving vehicle (ADV), comprising:
routing an ADV through execution of a first driving scenario that is active, the first driving scenario being one of a plurality of driving scenario types, each driving scenario type being associated with one or more stages to be executed while a corresponding driving scenario type is active;
based on an environmental condition around the ADV, entering a second driving scenario from the first driving scenario by setting the second driving scenario as active including inserting the second driving scenario as one of the one or more stages that are associated with the first driving scenario to be executed while the first driving scenario is active, resulting in a nesting of the second driving scenario within the first driving scenario such that when the second driving scenario exits, the first driving scenario automatically becomes active, while preserving planning and control data associated with the first driving scenario;
routing the ADV through execution of the second driving scenario; and
in response to exiting the second driving scenario, resuming execution of the first driving scenario which becomes active, at the one or more stages of the first driving scenario that remains to be executed based in part on the preserved planning and control data of the first driving scenario.

2. The method of claim 1 , wherein the plurality of driving scenario types includes at least two of: a default scenario, a stop sign scenario, an intersection scenario, a traffic light scenario, a pedestrian interaction scenario, or a side pass scenario.

3. The method of claim 1 , wherein the environmental condition around the ADV indicates at least one of: normal, a stop sign, an intersection, a traffic light, a pedestrian, or a road vehicle.

4. The method of claim 1 , further comprising
based on another environmental condition around the ADV, entering a third driving scenario by setting the third driving scenario as active, while suspending the second driving scenario;
routing the ADV through execution of the third driving scenario; and
when the third driving scenario exits, resuming execution of the second driving scenario which becomes active, at one or more stages of the second driving scenario that is remaining to be executed.

5. The method of claim 1 , wherein each of the one or more stages uniquely identifies one or more algorithms that are implemented to tailor generation of a vehicle path and a vehicle speed to the corresponding driving scenario type.

6. The method of claim 1 , wherein each of the plurality of driving scenario types defines a unique sequence of the one or more stages to be executed while the corresponding driving scenario type is active.

7. The method of claim 1 , wherein upon completion of the second driving scenario, the first driving scenario resumes execution of the one or more stages associated with the first driving scenario based on where the second driving scenario was inserted.

8. The method of claim 1 , wherein information associated with the first driving scenario is preserved through duration of the second driving scenario.

9. The method of claim 8 , wherein the information is stored in computer readable memory that is globally accessible.

10. The method of claim 1 , wherein configuration information for the one or more stages is stored in computer readable memory, capable of being retrieved during run-time.

11. 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:
routing an ADV through execution of a first driving scenario that is active, the first driving scenario being one of a plurality of driving scenario types, each driving scenario type being associated with one or more stages to be executed while a corresponding driving scenario type is active;
based on an environmental condition around the ADV, entering a second driving scenario from the first driving scenario by setting the second driving scenario as active including inserting the second driving scenario as one of the one or more stages that are associated with the first driving scenario to be executed while the first driving scenario is active, resulting in a nesting of the second driving scenario within the first driving scenario such that when the second driving scenario exits, the first driving scenario automatically becomes active, while preserving planning and control data associated with the first driving scenario;
routing the ADV through execution of the second driving scenario; and
in response to exiting the second driving scenario, resuming execution of the first driving scenario which becomes active, at the one or more stages of the first driving scenario that remains to be executed based in part on the preserved planning and control data of the first driving scenario.

12. The non-transitory machine-readable medium of claim 11 , wherein the plurality of driving scenario types includes at least two of: a default scenario, a stop sign scenario, an intersection scenario, a traffic light scenario, a pedestrian interaction scenario, or a side pass scenario.

13. The non-transitory machine-readable medium of claim 11 , wherein the environmental condition around the ADV indicates at least one of: normal, a stop sign, an intersection, a traffic light, a pedestrian, or a road vehicle.

14. The non-transitory machine-readable medium of claim 11 , wherein the operations further comprise:
based on another environmental condition around the ADV, entering a third driving scenario by setting the third driving scenario as active, while suspending the second driving scenario;
routing the ADV through execution of the third driving scenario; and
when the third driving scenario exits, resuming execution of the second driving scenario which becomes active, at one or more stages of the second driving scenario that is remaining to be executed.

15. The non-transitory machine-readable medium of claim 11 , wherein each of the one or more stages uniquely identifies one or more algorithms that are implemented to tailor generation of a vehicle path and a vehicle speed to the corresponding driving scenario type.

16. 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
routing an ADV through execution of a first driving scenario that is active, the first driving scenario being one of a plurality of driving scenario types, each driving scenario type being associated with one or more stages to be executed while a corresponding driving scenario type is active;
based on an environmental condition around the ADV, entering a second driving scenario from the first driving scenario by setting the second driving scenario as active including inserting the second driving scenario as one of the one or more stages that are associated with the first driving scenario to be executed while the first driving scenario is active, resulting in a nesting of the second driving scenario within the first driving scenario such that when the second driving scenario exits, the first driving scenario automatically becomes active, while preserving planning and control data associated with the first driving scenario;
routing the ADV through execution of the second driving scenario; and
in response to exiting the second driving scenario, resuming execution of the first driving scen

Assignees

• Baidu Usa Llc

Inventors

• Tao Jiaming
• Luo Qi
• Zhou Jinyun
• Xu Kecheng
• Wang Yu
• Jiang Shu
• Hu Jiangtao
• Miao Jinghao

Classifications

• B60W2552/05

  Type of road, e.g. motorways, local streets, paved or unpaved roads · CPC title

• B60W40/04

  Traffic conditions · CPC title

• B60W60/0011 Primary

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

• B60W2555/60

  Traffic rules, e.g. speed limits or right of way · CPC title

• G01S17/931

  of land vehicles · CPC title