Assertive vehicle detection model generation

Patent metadata

Field	Value
Publication number	US-12494125-B2
Application number	US-202217894074-A
Country	US
Kind code	B2
Filing date	Aug 23, 2022
Priority date	Dec 2, 2019
Publication date	Dec 9, 2025
Grant date	Dec 9, 2025

Abstract

There is disclosed herein examples of system and procedure for generating a model to be implemented within autonomous vehicles for identifying assertive vehicles at an intersection having stop indicators. The model can be generated via data-driven procedure where captures of the movement of vehicles through an intersection are analyzed and utilized for generating the model. The model may be provided to the autonomous vehicles and may be implemented by the autonomous vehicles for identifying assertive vehicles.

First claim

The invention claimed is:

1. A computer-implemented method, comprising:
capturing, by one or more autonomous vehicles, data representing surroundings of the one or more autonomous vehicles, including physical characteristics of an intersection and movement characteristics of vehicles within an interest zone, wherein the interest zone corresponds to the intersection having stop indicators in at least two directions;
identifying, by a processing device of an analysis system, a first portion of the data associated with one or more identified assertive vehicles and a second portion of the data associated with one or more identified non-assertive vehicles, wherein identifying the first portion of the data associated with one or more identified assertive vehicles comprises
identifying threshold positions of the intersection corresponding to positions where entry paths of the intersection crosses each other;
identifying an order in which a plurality of identified vehicles is expected to cross the threshold position;
identifying a first vehicle in the plurality of identified vehicles as an assertive vehicle responsive to the captured data indicating the first vehicle arrives at the threshold position prior to at least one other vehicle in the plurality of identified vehicles, where the at least one other vehicle has an earlier position in the order than the first vehicle;
generating a model to discriminate between assertive vehicles and non-assertive vehicles using the first portion of the data and the second portion of the data, wherein the model utilizes characteristics of a particular vehicle in the interest zone to predict when a vehicle is likely to be an assertive vehicle or a non-assertive vehicle, and the model produces results that are consistent with the analysis system in identifying the one or more identified assertive vehicles and the one or more identified non-assertive vehicles;
implementing the model on an autonomous vehicle to discriminate between assertive and non-assertive vehicles; and
taking an action, by the autonomous vehicle, based on results of the implemented model.

2. The computer-implemented method of claim 1 , wherein the characteristics of the particular vehicle includes velocity, acceleration, and position.

3. The computer-implemented method of claim 1 , wherein the interest zone comprises a buffer zone.

4. The computer-implemented method of claim 1 , wherein:
the interest zone includes an interior zone, and an intersection zone; and
the method further comprises defining locations of the interest zone, the interior zone, and the intersection zone based on physical characteristics of the intersection.

5. The computer-implemented method of claim 1 , wherein the movement characteristics of vehicles within the interest zone comprises:
indications of location of the vehicles captured at set intervals.

6. The computer-implemented method of claim 1 , wherein the movement characteristics of vehicles within the interest zone comprises:
timestamped indications of location of the vehicles as the vehicles proceed along entry paths of the intersection.

7. The computer-implemented method of claim 1 , wherein the identifying comprises:
determining a plurality of entry paths that are travelled by vehicles through the intersection; and
determining points of intersection of a given entry path with other entry paths.

8. The computer-implemented method of claim 1 , wherein the identifying comprises:
determining a right of way order of the vehicles within the interest zone, wherein the right of way order comprises an indication of an order of the vehicles should proceed through the intersection based on road rules and physical characteristics of the intersection.

9. The computer-implemented method of claim 8 , wherein the identifying comprises:
removing a vehicle from the right of way order and promoting vehicles lower in the order when a vehicle leaves the interest zone.

10. The computer-implemented method of claim 1 , wherein identifying the first portion of the data associated with one or more identified assertive vehicles comprises:
identifying asserting captures, wherein the asserting captures includes captures of movement characteristics of the assertive vehicle prior to the assertive vehicle arriving at the threshold position.

11. The computer-implemented method of claim 10 , wherein identifying the first portion of the data associated with one or more identified assertive vehicles comprises:
deriving characteristics from the asserting captures, wherein the characteristics are to be used as part of the first portion of the data, and to be used by the model to predict whether a given vehicle approaching an intersection is likely an assertive vehicle.

12. The computer-implemented method of claim 11 , wherein the derived characteristics includes: a distance of the asserting vehicle to a stop line/edge of an intersection zone.

13. The computer-implemented method of claim 11 , wherein the derived characteristics includes: a distance of the asserting vehicle to an edge of an interior zone.

14. The computer-implemented method of claim 11 , wherein the derived characteristics includes one or more of: a speed of the asserting vehicle, and an acceleration of the asserting vehicle.

15. The computer-implemented method of claim 11 , wherein the derived characteristics includes: whether the asserting vehicle had a lead vehicle.

16. The computer-implemented method of claim 11 , wherein the derived characteristics includes: a difference in a time the assertive vehicle arrived at the intersection and an earliest time that one of the vehicles that had not arrived at the threshold position or left the interest zone arrived at the intersection.

17. The computer-implemented method of claim 11 , wherein the derived characteristics includes: a right of way order of the vehicles.

18. One or more non-transitory computer-readable media having instructions stored thereon, wherein the instructions, in response to execution by a device, cause the device to:
capture data representing surroundings of one or more autonomous vehicles, including physical characteristics of an intersection and movement characteristics of vehicles within an interest zone, wherein the interest zone corresponds to the intersection having stop indicators in at least two directions;
identify a first portion of the data associated with one or more identified assertive vehicles and a second portion of the data associated with one or more identified non-assertive vehicles wherein identifying the first portion of the data associated with one or more identified assertive vehicles comprises
identifying threshold positions of the intersection corresponding to positions where entry paths of the intersection crosses each other;
identifying an order in which a plurality of identified vehicles is expected to cross the threshold position;
identifying a first vehicle in the plurality of identified vehicles as an assertive vehicle responsive to the captured data indicating the first vehicle arrives at the threshold position prior to at least one other vehicle in the plurality of identified vehicles, where the at least one other vehicle has an earlier position in the order than the first vehicle;
generate a model to discriminate between assertive vehicles and non-assertive vehicles using the first portion of the data and the second portion of the data, wherein the model produces results that are consistent with the identifying step in identifying the one or more identified assertive vehicles

Assignees

• Gm Cruise Holdings Llc

Inventors

• Ghafouri Amin
• Palli Prasanth
• Allan Jeremy

Classifications

• G06V20/58

  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

• G06V20/584

  of vehicle lights or traffic lights · CPC title

• B60W40/04

  Traffic conditions · CPC title

• B60W30/18154

  Approaching an intersection · CPC title