Intelligent vehicle navigation systems, methods, and control logic for multi-lane separation and trajectory extraction of roadway segments

Patent metadata

Field	Value
Publication number	US-10761535-B2
Application number	US-201816107272-A
Country	US
Kind code	B2
Filing date	Aug 21, 2018
Priority date	Aug 21, 2018
Publication date	Sep 1, 2020
Grant date	Sep 1, 2020

Abstract

Presented are systems and methods for extracting lane-level information of designated road segments by mining vehicle dynamics data traces. A method for controlling operation of a motor vehicle includes: determining the vehicle's location; identifying a road segment corresponding to the vehicle's location; receiving road-level data associated with this road segment; determining a turning angle and centerline for the road segment; receiving vehicle data indicative of vehicle locations and dynamics for multiple vehicles travelling on the road segment; determining, from this vehicle data, trajectory data indicative of start points, end points, and centerline offset distances for these vehicles; identifying total driving lanes for the road segment by processing the trajectory data with a clustering algorithm given the turning angle and centerline; extracting virtual trajectories for the driving lanes; and commanding a vehicle subsystem to execute a control operation based on an extracted virtual trajectory for at least one driving lane.

First claim

What is claimed:

1. A method for controlling operation of a motor vehicle, the method comprising:
determining, via a resident vehicle controller of the motor vehicle, a vehicle location of the motor vehicle;
conducting a geospatial query to identify a designated road segment corresponding to the vehicle location;
receiving, from a memory-stored map database, road-level data associated with the designated road segment;
determining, from the road-level data, a turning angle and a centerline for the designated road segment;
receiving connected vehicle data indicative of vehicle locations and dynamics for multiple motor vehicles while travelling on the designated road segment;
determining, from the connected vehicle data, trajectory data indicative of respective start points, end points, and centerline offset distances for the multiple motor vehicles;
identifying, based on the turning angle and the centerline, a number of driving lanes for the designated road segment, including processing the trajectory data with a clustering algorithm that applies a k-means clustering analysis that identifies the number of driving lanes as an estimated number of clusters, each of the clusters composed of a subset of the start points and/or end points with the corresponding centerline offset distances thereof proximate a common centroid;
extracting a respective virtual trajectory for each of the driving lanes; and
transmitting, via the resident vehicle controller, a command signal to a resident vehicle subsystem to execute a control operation based on at least one of the extracted virtual trajectories corresponding to at least one of the driving lanes of the designated road segment, the resident vehicle subsystem including an Advanced Driver Assistance System (ADAS) intersection assistance module, and the control operation including an automated steering maneuver and/or an automated braking maneuver adapted by the ADAS intersection assistance module based on the at least one of the extracted virtual trajectories.

2. The method of claim 1 , wherein determining the turning angle for the designated road segment includes:
determining, from the road-level data, an entry angle δ IN and an exit angle δ OUT , and
calculating the turning angle as θ T , where θ T =δ OUT −δ IN .

3. The method of claim 2 , wherein determining the centerline for the designated road segment includes:
determining, from the road-level data, intersection center point coordinates x 0 , y 0 ;
determining an entry centerline L IN as (y IN −y 0 )=δ IN (x IN −x 0 ); and
determining an exit centerline L OUT as (y OUT −y 0 )=δ OUT (x OUT −x 0 ).

4. The method of claim 1 , wherein determining the trajectory data includes estimating a respective start heading, a respective end heading, and a respective turning angle for a corresponding one of the driving lanes.

5. The method of claim 4 , wherein estimating the respective turning angle includes estimating the turning angle as θ 1 , where θ 1 =∫Ydt, and where Y is a yaw rate and dt is a time derivative.

6. The method of claim 5 , wherein each of the respective start points is identified as a first location whereat the yaw rate starts to increase or decrease away from a calibrated threshold estimate, and wherein each of the respective end points is identified as a second location whereat the yaw rate increases or decreases back to the calibrated threshold estimate.

7. The method of claim 1 , wherein the clustering algorithm identifies the number of driving lanes as the estimated number of clusters K, where:
K =Max(Diff pd )/ W lane

where Diff pd is a difference among start points centerline offset distances or end points centerline offset distances; and W lane is a standardized lane width corresponding to the designated road segment.

8. The method of claim 1 , wherein determining the centerline offset distances includes calculating, for each of the multiple motor vehicles, a respective perpendicular distance PD from the centerline as:



aX
+
bY
+
c



√

(

a
2

+

b
2

)

where X and Y are Cartesian coordinates for a start point or end point, a is an entry angle, b is an integer, c=y 0 −δ IN x 0 , with an entry angle δ IN and intersection center point coordinates x 0 , y 0 , and aX+bY+c is a linear equation representing the centerline.

9. The method of claim 1 , wherein identifying the designated road segment corresponding to the vehicle location includes determining a bounding box that delineates a set of geographical boundaries surrounding the vehicle's location.

10. The method of claim 1 , wherein the number of driving lanes for the designated road segment includes first and second driving lanes, and wherein the virtual trajectories include a first virtual trajectory corresponding to the first driving lane and a second virtual trajectory, distinct from the first virtual trajectory, corresponding to the second driving lane.

11. The method of claim 10 , wherein the number of driving lanes for the designated road segment includes a third driving lane, and wherein the virtual trajectories include third and fourth virtual trajectories, distinct from the first and second virtual trajectories, corresponding to the third driving lane.

12. The method of claim 1 , wherein determining the turning angle and centerline, determining the trajectory data, identifying the number of driving lanes, and extracting the virtual trajectories are executed by a remote system server computer off-board from the motor vehicle.

13. The method of claim 1 , wherein the resident vehicle subsystem further includes a vehicle navigation system with an electronic display device, and wherein the control operation further includes saving the number of driving lanes and the extracted virtual trajectories in the memory-stored map database and/or displaying an indication of the at least one of the extracted virtual trajectories on the electronic display device.

14. A method for controlling operation of a motor vehicle, the motor vehicle including a vehicle controller, a vehicle steering system, a vehicle powertrain system, and a vehicle braking system, the method comprising:
receiving, via the vehicle controller of the motor vehicle, geodetic datum indicative of a real-time vehicle location of the motor vehicle;
conducting a geospatial query to identify a designated road segment corresponding to the real-time vehicle location;
receiving, from a memory-stored map database, road-level data including a road segment count and/or lane alignment information of the designated road segment;
determining, from the road-level data, a turning angle and a centerline for the designated road segment;
receiving connected vehicle data indicative of vehicle locations and dynamics for multiple motor vehicles while travelling on the designated road segment;
determining, from the connected vehicle data, trajectory data indicative of respective start points, end points, and centerline offset distances for the multiple motor

Assignees

• Gm Global Tech Operations Llc

Inventors

• Chen Shu
• Bai Fan
• Grimm Donald K
• Chen Jinzhu
• Yu Bo
• Bojanowski David E

Classifications

• G01C21/3896

  Transmission of map data from central databases · CPC title

• G01C21/3815

  Road data · 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

• G08G1/0141 Primary

  for traffic information dissemination · CPC title

• G08G1/096791

  where the origin of the information is another vehicle · CPC title