LANE MONITORING WITH ELECTRONIC HORIZON

• US 20140379164A1
• Filed: 06/20/2013
• Published: 12/25/2014
• Est. Priority Date: 06/20/2013
• Status: Active Grant

• Current Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Original Assignee: Ford Global Technologies, LLC (Ford Motor Company)
• Inventors: Pilutti, Thomas E., Rupp, Matt Y., Wolski, Brian, Joh, Peter G., Spero, Dorian Jack
• Granted Patent: US 8,996,197 B2
• Time in Patent Office: Days
• US Class Current: 701/1
• CPC Class Codes: B60W 2050/0091 of control inputs
• CPC Class Codes: B60W 2050/0215 Sensor drifts or sensor failures
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

Apparatus for a vehicle operated on a roadway having lane markers includes an optical sensor providing optical data of the roadway. A first lane model is stored in an electronic memory in response to detected lane markers in the optical data. An electronic horizon system tracks a position of the vehicle and provides roadway data in response to the position. A second lane model is stored in the electronic memory in response to the roadway data. A confidence checker compares a discrepancy between the first and second lane models to a threshold in order to determine a confidence level. An output selector selects the first lane model when lane markers are detected in the optical data, and selects the second lane model if the lane markers are not detected in the optical data and the confidence level is greater than a predetermined level.

Claims

1. Apparatus for a vehicle operated on a roadway having lane markers, comprising:

an optical sensor providing optical data of the roadway;

a first lane model stored in an electronic memory in response to detected lane markers in the optical data;

an electronic horizon system tracking a position of the vehicle and providing roadway data in response to the position;

a second lane model stored in the electronic memory in response to the roadway data;

a confidence checker comparing a discrepancy between the first and second lane models to a threshold in order to determine a confidence level; and

an output selector that selects the first lane model when lane markers are detected in the optical data, and that selects the second lane model if the lane markers are not detected in the optical data and the confidence level is greater than a predetermined level.

2. The apparatus of claim 1 further comprising a driver assistance system that controls a driver assistance parameter, wherein the driver assistance system is coupled to the output selector and adjusts the assistance parameter in response to the model output by the output selector.

3. The apparatus of claim 1 wherein the electronic horizon system includes a map database representing the roadway as a plurality of segments along a pathline, and wherein the second lane model generates a virtual lane boundary by lateral shifting of the pathline according to a distance between the pathline and the first lane model.

4. The apparatus of claim 3 wherein the electronic horizon system is comprised of a GPS navigation system.

5. The apparatus of claim 3 wherein the electronic horizon system is comprised of a dead-reckoning system.

8. The apparatus of claim 1 further comprising a pattern recognizer receiving the optical data and identifying the lane markers in the optical data to generate the first lane model.

9. The apparatus of claim 8 wherein the lane markers recognized by the pattern recognizer include painted lane lines and road edges.

6-7. -7. (canceled)

10. A method of detecting a lane position of a vehicle on a roadway, comprising the steps of:

maintaining a first lane model based on optical sensor data;

maintaining a second lane model based on monitored vehicle position and a map database;

evaluating a similarity of the models;

selecting an active lane model in response to whether lane markers are being detected in the optical sensor data and whether the similarity is above a predetermined similarity.

11. The method of claim 10 wherein the first lane model includes a lane heading and a lane marker offset distance, wherein the second lane model includes a pathline heading and a virtual offset distance, and wherein the method further comprising the steps of:

obtaining a pathline representing the roadway from the map database;

determining a point on the pathline closest to the vehicle;

determining the pathline heading in response to a direction of the pathline at the closest point;

determining a lateral offset distance between the vehicle and the closest point;

determining the virtual offset distance by shifting the pathline according to a difference between the lateral offset distance of the pathline and the lane marker offset distance of the first lane model.

12. The method of claim 11 wherein the step of evaluating similarity is comprised of:

monitoring a difference between the lateral offset distance and the lane marker offset for a plurality of time samples;

determining a variance among the plurality of monitored differences; and

detecting a similarity above the predetermined similarity if the difference between the pathline heading and the lane heading is less than a first threshold and if the variance is less than the second threshold.

13. The method of claim 11 wherein the step of evaluating similarity is comprised of:

monitoring a difference between the lateral offset distance and the lane marker offset for a plurality of time samples;

determining a variance among the plurality of monitored differences;

incrementing a similarity count if the difference between the pathline heading and the lane heading is less than a first threshold and if the variance is less than the second threshold; and

detecting a similarity above the predetermined similarity if the similarity count is above a third threshold.

14. The method of claim 10 wherein the first lane model is maintained using pattern recognition to identify lane markers in the optical sensor data including painted lane lines and road edges.

15. The method of claim 10 wherein the vehicle position is obtained using a GPS navigation system in the vehicle.

16. The method of claim 10 wherein the vehicle position is obtained using a dead-reckoning system in the vehicle.

17. Apparatus for a vehicle operated on a roadway having lane markers, comprising:

an optical sensor providing optical data of the roadway;

a first lane model stored in an electronic memory in response to detected lane markers in the optical data;

an electronic horizon system tracking a position of the vehicle and providing roadway data in response to the position;

a second lane model stored in the electronic memory in response to the roadway data;

a confidence checker comparing a discrepancy between the first and second lane models to a threshold in order to determine a confidence level; and

an output selector that selects the first lane model when lane markers are detected in the optical data, and that selects the second lane model if the lane markers are not detected in the optical data and the confidence level is greater than a predetermined level;

wherein the first lane model includes an optical heading (φ

_Lane), (wherein the second lane model includes an electronic horizon heading (φ

_EH), and wherein the discrepancy compared by the confidence checker to the threshold is comprised of an absolute value of a difference φ

_EH−

φ

_Lane.

18. Apparatus for a vehicle operated on a roadway having lane markers, comprising:

an optical sensor providing optical data of the roadway;

a first lane model stored in an electronic memory in response to detected lane markers in the optical data;

an electronic horizon system tracking a position of the vehicle and providing roadway data in response to the position;

a second lane model stored in the electronic memory in response to the roadway data;

a confidence checker comparing a discrepancy between the first and second lane models to a threshold in order to determine a confidence level; and

an output selector that selects the first lane model when lane markers are detected in the optical data, and that selects the second lane model if the lane markers are not detected in the optical data and the confidence level is greater than a predetermined level;

wherein the first lane model includes an optical vehicle to lane offset distance (d_Lane), wherein the second lane model includes an electronic horizon vehicle to pathline offset distance (d_EH), and wherein the discrepancy compared by the confidence checker to the threshold is comprised of a variance of d_EH−

d_Lane.