Lane-keeping system for automated vehicles

1. A lane-keeping system suitable for use on a vehicle, said system comprising:

a camera configured to detect a lane-marking of a roadway travel-lane traveled by the vehicle;

an inertial-measurement-unit configured to determine relative-motion of the vehicle; and

a controller in communication with the camera and the inertial-measurement-unit, wherein when the lane-marking is detected by the camera, said controller is configured to determine a centerline within the roadway travel-lane defined by the lane-marking,

determine a last-position of the vehicle relative to the centerline of the roadway travel-lane based on the lane-marking detected by the camera,

determine a current-vector used to steer the vehicle towards the centerline of the roadway travel-lane based on the last-position, and

determine an offset-vector indicative of motion of the vehicle relative to the centerline of the roadway travel-lane, and wherein

when the lane-marking is not detected by the camera said controller is configured to

determine an offset-position of the vehicle relative to the last-position of the vehicle based on information from the inertial-measurement-unit,

determine a correction-vector used to steer the vehicle from the offset-position towards the centerline of the roadway travel-lane based on the last-position and the offset-vector, and steer the vehicle according to the correction-vector.

2. The system in accordance with claim 1 , wherein the controller is further configured to determine a last-vector based on a temporal-history of the current-vector, and the correction-vector is further based on the last-vector.

3. The system in accordance with claim 1 , wherein the system includes a speed-sensor configured to measure speed of the vehicle, and the offset-position is also determined based on the measured speed.

4. A method for controlling a vehicle, said method comprising:

receiving a video-signal from a camera;

receiving a vehicle position-signal from an inertial-measurement-unit;

detecting, by a controller, a lane-marking of a roadway travel-lane based on the video-signal;

determining, by the controller, a centerline within the roadway travel-lane defined by the lane-marking;

determining a last-position of the vehicle relative to the centerline of the roadway travel-lane based on the lane-marking;

determining a current-vector based on the centerline of the roadway travel-lane;

determining an offset-vector indicative of motion of the vehicle relative to the centerline based on the position-signal;

steering the vehicle according to the current-vector in an automated-mode when the lane marking is detected by the controller;

determining, with the controller, whether the lane-marking is detected:

when the lane-marking is not detected by the controller for a time less than a time-threshold;

determining an offset-position relative to the last-position based on the position-signal;

determining a correction-vector used to steer the vehicle from the offset-position towards the centerline of the roadway travel-lane based on the last-position and the offset-vector;

steering the vehicle according to the correction-vector in an automated-mode;

when the lane-marking is not detected by the controller for a time equal to or greater than a time-threshold,

steering the vehicle in a manual-mode.

5. The method in accordance with claim 4 , wherein the method includes the step of receiving a speed-signal from a vehicle speed-sensor, and the step of determining the offset-vector is further based on a speed of the vehicle.

6. The method in accordance with claim 4 , wherein the method includes determining a last-vector based on a temporal-history of the current-vector, and the correction-vector is further based on the last-vector.

7. The method in accordance with claim 6 , wherein the last-vector is a running-average of the last-vector data points stored in a memory of the controller.