IP Library Granted Patent US 11,760,384
Granted Patent B2
US 11,760,384 · App. 16/852,060 · Granted Sep 19, 2023

Methods and systems for determining trajectory estimation order for vehicles

Inventors: Pavel Sergeevich Hud (Minsk, BY); Victor Igorevich Otliga (Minsk, BY)
Assignee: YANDEX SELF DRIVING GROUP LLC
B60W60/0027B60W60/0011G06N20/00G06V20/56G08G1/0125G08G1/0145
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,760,384
App. No.
16/852,060
Granted
Sep 19, 2023
Kind
B2
Abstract

A method of and processor for determining a trajectory estimation order for vehicles are disclosed. The processor has access to a section of a road map corresponding to surroundings of the one of the vehicles, and road rules associated therewith. The method includes identifying pairs of vehicles that have intersecting potential trajectories and vehicle priority information indicative of priorities of vehicles on the section of the road map. Based on the vehicle priority information, the method includes determining a trajectory estimation order for vehicles on the section of the road map, such that a given vehicle having priority over another vehicle in the vehicle priority information is above another vehicle in the trajectory estimation order.

Claims (56)

1. A method of controlling operation of an autonomous vehicle including determining a trajectory estimation order for vehicles driving in surroundings of the autonomous vehicle, the autonomous vehicle being communicatively coupled to a processor, the processor having access to information indicative of:

(i) a section of a road map corresponding to the surroundings of the autonomous vehicle, and

(ii) road rules associated with the section of the road map,

the method being executable by the processor, the method comprising:

identifying, by the processor, pairs of vehicles, including the autonomous vehicle, on the section of the road map that have intersecting potential trajectories; and

identifying, by the processor, vehicle priority information indicative of priorities of the vehicles, including the autonomous vehicle, on the section of the road map, the identifying comprising:

using, by the processor, the road rules for determining which one in a respective pair of vehicles has priority over the other one in the respective pair of vehicles;

generating, by the processor, at least one graph structure having vertices and edges,

a given one of the at least one graph structure being a respective hierarchical structure representing a respective priority-based hierarchy between the vehicles in the section of the road map;

a given edge connecting a pair of vertices;

the pair of vertices being indicative of the respective pair of vehicles on the section of the road map; and

the given edge representing which one of a first one in the respective pair of vehicles has priority over a second one in the respective pair of vehicles; and

based on the vehicle priority information,

determining, by the processor, a trajectory estimation order for the vehicles on the section of the road map, including the autonomous vehicle,

such that a given vehicle having priority over another vehicle in the vehicle priority information is above another vehicle in the trajectory estimation order;

based on the trajectory estimation order, determining, by the processor, a target trajectory for the autonomous vehicle; and

causing, by the processor, the autonomous vehicle to move along the target trajectory.

2. The method of claim 1 , wherein the determining the target trajectory for the autonomous vehicle comprises determining estimated trajectories of the vehicles on the section of the road map,

such that:

(i) at least one estimated trajectory of the given vehicle is determined prior to determining at least one estimated trajectory of the another vehicle; and

(ii) the at least one estimated trajectory of the another vehicle is determined based on the at least one estimated trajectory of the given vehicle.

3. The method of claim 2 , wherein the determining the target trajectory for the autonomous vehicle further comprises:

inputting, by the processor, the estimated trajectories of the vehicles into a Machine Learned Algorithm (MLA),

the MLA being configured to employ at least the estimated trajectories of the vehicles for outputting the target trajectory of the one of the vehicles.

4. The method of claim 3 , wherein the MLA is further configured to employ kinematic data about at least one of the vehicles for outputting the target trajectory of the autonomous vehicle.

5. The method of claim 4 , wherein the kinematic data comprises at least one of:

a position of the at least one of the vehicles;

a speed of the at least one of the vehicles; and

an acceleration of the at least one of the vehicles.

6. The method of claim 4 , wherein the kinematic data is gathered by a sensor system communicatively coupled to the autonomous vehicle.

7. The method of claim 1 , wherein the processor further has access to information indicative of positions of the vehicles on the section of the road map.

8. The method of claim 7 , wherein the information indicative of the positions is gathered by a sensor system communicatively coupled to the autonomous vehicle.

9. The method of claim 8 , wherein the autonomous vehicle is equipped with the sensor system.

10. The method of claim 1 , wherein the respective hierarchical structure representing the respective priority-based hierarchy between the vehicles has on top thereof a respective main vehicle, the respective main vehicle being a least affected vehicle by the vehicles in the respective priority-based hierarchy than any other vehicle in the respective priority-based hierarchy.

11. The method of claim 1 , wherein the trajectory estimation order for the respective priority-based hierarchy starts with the respective main vehicle.

12. The method of claim 11 , wherein the determining the target trajectory for the autonomous vehicle comprises generating at least one estimated trajectories of vehicles being above the autonomous vehicle in the order, starting with the respective main vehicle and going down the order.

13. The method of claim 12 , wherein the method comprises not determining the at least one estimated trajectory for vehicles below the autonomous vehicle in the order.

14. The method of claim 1 , wherein the another vehicle is another autonomous vehicle.

15. The method of claim 14 , wherein the method further comprises transmitting information indicative of the trajectory estimation order to the another vehicle.

16. The method of claim 14 , wherein the processor of the autonomous vehicle has access to kinematic data about at least one of the vehicles, and wherein the method further comprises transmitting the kinematic data to the another vehicle.

17. A processor for controlling operation of an autonomous vehicle including determining a trajectory estimation order for vehicles driving in surroundings of the autonomous vehicle, the autonomous vehicle being communicatively coupled to the processor, the processor having access to information indicative of:

(i) a section of a road map corresponding to the surroundings of the autonomous vehicle, and

(ii) road rules associated with the section of the road map,

the processor being configured to:

identify pairs of vehicles, including the autonomous vehicle, on the section of the road map that have intersecting potential trajectories;

identify vehicle priority information indicative of priorities of the vehicles, including the autonomous vehicle, on the section of the road map, to identify vehicle priority information the processor being configured to:

use the road rules for determining which one in a respective pair of vehicles has priority over the other one in the respective pair of vehicles;

generate at least one graph structure having vertices and edges, a given one of the at least one graph structure being a respective hierarchical structure representing a respective priority-based hierarchy between the vehicles in the section of the road map;

a given edge connecting a pair of vertices;

the pair of vertices being indicative of the respective pair of vehicles on the section of the road map; and

the given edge representing which one of a first one in the respective pair of vehicles has priority over a second one in the respective pair of vehicles; and

based on the vehicle priority information,

determine trajectory estimation order for vehicles on the section of the road map, including the autonomous vehicle,

such that a given vehicle having priority over another vehicle in the vehicle priority information is above another vehicle in the trajectory estimation order;

based on the trajectory estimation order, determine a target trajectory for the autonomous vehicle; and

cause the autonomous vehicle to move along the target trajectory.

Assignments (5)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 9, 2024
From: DIRECT CURSUS TECHNOLOGY L.L.C
To: Y.E. HUB ARMENIA LLC
Reel/Frame 068534/0537 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 2, 2023
From: YANDEX SELF DRIVING GROUP LLC
To: DIRECT CURSUS TECHNOLOGY L.L.C
Reel/Frame 065447/0048 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 3, 2023
From: OTLIGA, VICTOR IGOREVICH; HUD, PAVEL SERGEEVICH
To: YANDEXBEL LLC
Reel/Frame 062580/0417 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 3, 2023
From: YANDEX.TAXI LLC
To: YANDEX SELF DRIVING GROUP LLC
Reel/Frame 062580/0702 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 3, 2023
From: YANDEXBEL LLC
To: YANDEX.TAXI LLC
Reel/Frame 062581/0829 →