Scenario aware perception system for an automated vehicle

Patent metadata

Field	Value
Publication number	US-11604474-B2
Application number	US-202017137336-A
Country	US
Kind code	B2
Filing date	Dec 29, 2020
Priority date	Mar 22, 2016
Publication date	Mar 14, 2023
Grant date	Mar 14, 2023

Abstract

A scenario aware perception system (10) suitable for use on an automated vehicle includes a traffic-scenario detector (14), an object-detection device (24), and a controller (32). The traffic-scenario detector (14) is used to detect a present-scenario (16) experienced by a host-vehicle (12). The object-detection device (24) is used to detect an object (26) proximate to the host-vehicle (12). The controller (32) is in communication with the traffic-scenario detector (14) and the object-detection device (24). The controller (32) configured to determine a preferred-algorithm (36) used to identify the object (26). The preferred-algorithm (36) is determined based on the present-scenario (16).

First claim

We claim:

1. A method for controlling a host vehicle, comprising:
determining a present traffic scenario of a plurality of possible traffic scenarios of the host vehicle, wherein each possible traffic scenario characterizes a configuration of a roadway;
selecting a respective object identification algorithm associated with the present traffic scenario, wherein the object identification algorithm relates to an expected perspective-view of another vehicle that is to be identified in accordance with the object identification algorithm; and
identifying a target vehicle proximate to the host vehicle using the selected object identification algorithm.

2. The method of claim 1 , wherein the selected object identification algorithm is to identify the target vehicle based on movement of the target vehicle in an expected direction of travel on the roadway characterized by the present traffic scenario.

3. The method of claim 1 , wherein identifying the target vehicle proximate to the host vehicle using the selected object identification algorithm comprises:
receiving a radar reflection pattern of the target vehicle;
comparing the radar reflection pattern of the target vehicle to a plurality of stored reflection patterns associated with the selected object identification algorithm; and
identifying the target vehicle based on the comparison.

4. The method of claim 1 , wherein determining the present traffic scenario of the host vehicle comprises:
receiving coordinates defining a location of the host vehicle;
determining a configuration of a roadway at the location of the host vehicle using map data; and
based on the configuration of the roadway at the location, determining the present traffic scenario.

5. The method of claim 4 , wherein determining the present traffic scenario of the host vehicle comprises:
using sensor data to determine the configuration of a roadway at the location of host vehicle; and
based on the configuration of the roadway, determining the present traffic scenario.

6. The method of claim 1 , wherein the expected perspective-view of the other vehicle relates to a side-view of the other vehicle.

7. The method of claim 1 , wherein the expected perspective-view of the other vehicle relates to a rear-view of the other vehicle.

8. The method of claim 1 , wherein the expected perspective view of the other vehicle relates to a combination of a side-view and a rear-view of the other vehicle.

9. A host vehicle comprising:
a traffic scenario detector to determine a present traffic scenario of a plurality of possible traffic scenarios of the host vehicle, wherein each possible traffic scenario characterizes a configuration of a roadway;
a controller to select a respective object identification algorithm associated with the present traffic scenario, wherein the object identification algorithm relates to an expected perspective-view of another vehicle that is to be identified in accordance with the object identification algorithm; and
an object detection device to identify a target vehicle proximate to the host vehicle using the selected object identification algorithm.

10. The host vehicle of claim 9 , wherein the selected object identification algorithm is to identify the target vehicle based on movement of the target vehicle in an expected direction of travel on the roadway characterized by the present traffic scenario.

11. The host vehicle of claim 9 , wherein identification of the target vehicle proximate to the host vehicle using the selected object identification algorithm includes:
identification of a radar reflection pattern of the target vehicle;
comparison of the radar reflection pattern of the target vehicle to a plurality of stored reflection patterns associated with the selected object identification algorithm; and
identification of the target vehicle based on the comparison.

12. The host vehicle of claim 9 , wherein determination of the present traffic scenario of the host vehicle includes:
identification of coordinates defining a location of the host vehicle;
determination of determining a configuration of a roadway at the location of the host vehicle using map data; and
based on the configuration of the roadway at the location, determination of the present traffic scenario.

13. The host vehicle of claim 12 , wherein determination of the present traffic scenario of the host vehicle includes:
determination, based on sensor data, of a configuration of a roadway at the location of host vehicle; and
based on the configuration of the roadway, determination of the present traffic scenario.

14. The host vehicle of claim 9 , wherein the expected perspective-view of the other vehicle relates to a side-view of the other vehicle.

15. The host vehicle of claim 9 , wherein the expected perspective-view of the other vehicle relates to a rear-view of the other vehicle.

16. The host vehicle of claim 9 , wherein the expected perspective view of the other vehicle relates to a combination of a side-view and a rear-view of the other vehicle.

17. At least one non-transitory computer-readable media comprising instructions that, upon execution of the instructions by at least one processor of a host vehicle, are to cause the host vehicle to:
determine a present traffic scenario of a plurality of possible traffic scenarios of the host vehicle, wherein each possible traffic scenario characterizes a configuration of a roadway;
select a respective object identification algorithm associated with the present traffic scenario, wherein the object identification algorithm relates to an expected perspective-view of another vehicle that is to be identified in accordance with the object identification algorithm; and
identify a target vehicle proximate to the host vehicle using the selected object identification algorithm.

18. The at least one non-transitory computer-readable media of claim 17 , wherein the expected perspective-view of the other vehicle relates to a side-view of the other vehicle.

19. The at least one non-transitory computer-readable media of claim 17 , wherein the expected perspective-view of the other vehicle relates to a rear-view of the other vehicle.

20. The at least one non-transitory computer-readable media of claim 17 , wherein the expected perspective view of the other vehicle relates to a combination of a side-view and a rear-view of the other vehicle.

Assignees

• Motional Ad Llc

Inventors

• Xu Wenda
• Snider Jarrod M
• Wei Junqing

Classifications

• B60W2556/50

  of positioning data, e.g. GPS [Global Positioning System] data · CPC title

• G01S17/931

  of land vehicles · CPC title

• B60W2050/0083

  Setting, resetting, calibration · CPC title

• G01S13/867

  Combination of radar systems with cameras · CPC title

• B60W2554/00

  Input parameters relating to objects · CPC title