IP Library › Granted Patent US 11,320,284
Granted Patent B2
US 11,320,284 · App. 16/212,044 · Granted May 3, 2022

Real-time lane departure detection using map shape points and trajectory histories

Inventors: M. Imran Hayee (Duluth, MN); Muhammad Faizan (Duluth, MN); Shah Hussain (Duluth, MN)
Assignee: Regents of the University of Minnesota
G01C21/3697B60Q9/00B62D15/025
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 11,320,284
App. No.
16/212,044
Filed
Dec 6, 2018
Granted
May 3, 2022
Kind
B2
Art Unit
3664
USPC
701/41
Abstract

A method includes accessing information stored for positions along a road and using the accessed information to identify an expected trajectory for a vehicle. Position information for the vehicle is received from a global positioning system for two different time points and is used to determine a trajectory of the vehicle. The trajectory of the vehicle and the expected trajectory are used to determine a lateral offset of the vehicle from the expected trajectory and the lateral offset is used to determine when to issue a lane departure warning for the vehicle.

Claims (64)

1. A method comprising:

accessing information stored for positions along a road;

using the accessed information to identify an expected trajectory for a vehicle;

receiving erroneous positions for the vehicle from a global positioning system for two different time points and determining a trajectory of the vehicle by determining a difference between the erroneous positions for the two different time points;

using the trajectory of the vehicle and the expected trajectory to determine a lateral offset of the vehicle from the expected trajectory; and

using the lateral offset to determine when to issue a lane departure warning for the vehicle by summing a plurality of lateral offsets to form a total lateral offset and comparing the total lateral offset to a threshold; and

using the values of consecutive lateral offsets to determine when to reset the total lateral offset to zero such that the total lateral offset is reset to zero when a selected number of the consecutive lateral offsets are each less than a second threshold.

2. The method of claim 1 wherein the threshold is calculated based on the width of the vehicle and the width of a lane of the road.

3. The method of claim 1 wherein accessing information stored for positions along a road comprises accessing road-level information for a multi-lane road.

4. A vehicle comprising:

a global positioning system providing coordinates for erroneous positions of the vehicle; and

a processor:

determining differences between coordinates for the erroneous positions of the vehicle to determine trajectories of the vehicle;

using information about locations on a road to identify a preferred trajectory for the vehicle;

using differences between the determined trajectories and the preferred trajectory to identify lane departure events by determining a lateral offset for each determined trajectory, accumulating a plurality of lateral offsets to form a total lateral offset, and comparing the total lateral offset to a lane departure threshold to identify a lane departure event; and

using the values of consecutive lateral offsets to determine when to reset the total lateral offset to zero such that the total lateral offset is reset to zero when a selected number of the consecutive lateral offsets are each less than a second threshold.

5. The vehicle of claim 4 wherein the lane departure threshold is calculated based on the width of the vehicle and the width of a lane of the road.

6. The vehicle of claim 4 wherein the locations along the road are not positioned in a lane that the vehicle is traveling within.

7. A system comprising:

a global positioning system that identifies a respective erroneous position of a vehicle at each of a series of time points;

a memory containing information for locations along a road; and

a processor that for each time point:

determines a difference between an erroneous position of the vehicle from the global positioning system for the time point and an erroneous position of the vehicle from the global positioning system for a previous time point to determine a current trajectory for the vehicle at the time point,

uses the information for the locations along the road to determine a preferred trajectory at the time point, and

identifies a lane departure based on a lateral distance based on a difference between the current trajectory at the time point and the preferred trajectory at the time point wherein the processor identifies the lane departure by summing a plurality of lateral distances determined from the preferred trajectory for a plurality of time points to form a total lateral distance; and

uses the values of a series of consecutive lateral distances to determine when to reset the total lateral distance to zero such that the processor resets the total lateral distance to zero when each of the series of consecutive lateral distances is smaller than a threshold.

8. The system of claim 7 wherein the locations along the road are outside of a lane that the vehicle is traveling in.

9. The system of claim 7 wherein the processor determines the preferred trajectory by setting a constant value for changes in the preferred trajectory at a set of locations along the road.

10. A method comprising:

accessing information stored for positions along a road;

using the accessed information to identify an expected trajectory for a vehicle through steps comprising:

for each of a plurality of positions, determining a direction from the position to a next position along the road; and

averaging the directions determined for the positions in the plurality of positions to determine the expected trajectory;

receiving erroneous positions for the vehicle from a global positioning system for two different time points and determining a trajectory of the vehicle by determining a difference between the erroneous positions for the two different time points;

using the trajectory of the vehicle and the expected trajectory to determine a lateral offset of the vehicle from the expected trajectory; and

using the lateral offset to determine when to issue a lane departure warning for the vehicle.

11. A method comprising:

accessing information stored for positions along a road;

using the accessed information to identify an expected trajectory for a vehicle through steps comprising:

for each of a plurality of positions:

determining a direction from the position to a next position along the road; and

determining a difference between a direction determined for the position and a direction determined for the next position along the road; and

averaging the differences determined for the positions in the plurality of positions to determine an average change in the expected trajectory across the plurality of positions; and

for each of the plurality of positions, calculating the expected trajectory at the position by adding the average change in the expected trajectory to an expected trajectory calculated for a previous position along the road;

receiving erroneous positions for the vehicle from a global positioning system for two different time points and determining a trajectory of the vehicle by determining a difference between the erroneous positions for the two different time points;

using the trajectory of the vehicle and the expected trajectory to determine a lateral offset of the vehicle from the expected trajectory; and

using the lateral offset to determine when to issue a lane departure warning for the vehicle.

12. A vehicle comprising:

a global positioning system providing coordinates for erroneous positions of the vehicle; and

a processor:

determining differences between coordinates for the erroneous positions of the vehicle to determine trajectories of the vehicle;

using information about locations on a road to identify a preferred trajectory for the vehicle through steps comprising:

for each of a plurality of locations on the road, determining a direction from the location to a next location along the road; and

averaging the directions determined for the locations in the plurality of locations to determine the preferred trajectory; and

using differences between the determined trajectories and the preferred trajectory to identify lane departure events.

13. A vehicle comprising:

a global positioning system providing coordinates for erroneous positions of the vehicle; and

a processor:

determining differences between coordinates for the erroneous positions of the vehicle to determine trajectories of the vehicle;

using information about locations on a road to identify a preferred trajectory for the vehicle through steps comprising:

for each of a plurality of locations along the road, determining a change in direction needed to reach the location from a respective previous location along the road;

averaging the needed changes in direction to produce an average change in direction; and

setting the preferred trajectory based on the average change in direction; and

using differences between the determined trajectories and the preferred trajectory to identify lane departure events.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 9, 2020
From: FAIZAN, MUHAMMAD; HUSSAIN, SHAH
To: REGENTS OF THE UNIVERSITY OF MINNESOTA
Reel/Frame 051463/0959 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 9, 2019
From: HAYEE, IMRAN
To: REGENTS OF THE UNIVERSITY OF MINNESOTA
Reel/Frame 051218/0957 →
Continuity (2)
Provisional Application 62599496 · Dec 15, 2017
Related Publication 20190186948A1 · Jun 20, 2019
Cited By (1)
US 12,703,360