Apparatus and method for estimating position in automated valet parking system

1. An apparatus for estimating a position in an automated valet parking system, the apparatus comprising:

a front camera configured to capture a front image of a vehicle;

a front camera processor configured to process the front image of the vehicle received from the front camera;

a surround view monitor (SVM) processor configured to recognize a short-distance lane and a stop line by processing a surround view image of the vehicle;

a map data unit configured to store a high definition map; and

a controller configured to:

download a map comprising an area set as a parking zone from the map data unit when an entry of the vehicle to a parking lot is identified, and

correct a position measurement value of the vehicle by performing map matching based on results of a recognition and processing of the front camera processor and the SVM processor and the parking lot map of the map data unit, when an automated valet parking (AVP) start position is recognized based on the short-distance lane and stop line recognized by the SVM processor and when it is determined that the vehicle has parked at the AVP start position by receiving GPS information received from a GPS receiver or a signal, indicating that the vehicle has parked, from AVP infrastructure installed in the parking lot,

wherein the controller comprises a vehicle behavior prediction unit configured to predict a behavior of the vehicle through dead reckoning based on the GPS information received from the GPS receiver and a vehicle steering wheel angle, yaw rate and wheel speed received from a vehicle sensor unit, and

wherein the controller comprises a map-matching unit configured to perform the map matching based on lane fusion data in which a long-distance lane recognized by the front camera processor and the short-distance lane and stop line recognized by the SVM processor have been fused, parking lot map data from the map data unit, and vehicle behavior data for each time predicted through dead reckoning.

2. The apparatus of claim 1 , wherein the controller is configured to:

predict a behavior of the vehicle through dead reckoning when the AVP start position is recognized, and

estimate an AVP initial position of the vehicle by fusing the position measurement value of the vehicle corrected through the map matching and the predicted behavior of the vehicle.

3. The apparatus of claim 1 , wherein the map-matching unit is configured to compute a position and rotation correction quantity in which a distance error between sensor data and map data is minimized using iterative closest point (ICP) logic.

4. The apparatus of claim 1 , wherein the controller comprises a position fusion unit configured to fuse a vehicle pose output as results of the map matching and GPS information of a vehicle position predicted through dead reckoning.

5. The apparatus of claim 4 , wherein:

the controller comprises a fail-safe diagnosis unit configured to receive the vehicle position and flags output by the position fusion unit and to perform fail-safe diagnosis, and

the fail-safe diagnosis unit is configured to perform the fail-safe diagnosis using a distribution chart configured with estimated positioning results in which positioning results at past timing have been projected on current timing and positioning results input at current timing.

6. The apparatus of claim 4 , wherein the vehicle pose comprises one or more of longitude, latitude, heading, covariance, warning/fail/safe, flags and a lane offset.

7. A method of estimating a position in an automated valet parking system, the method comprising:

capturing, by a front camera, a front image of a vehicle;

processing, by a front camera processor, the front image of the vehicle received from the front camera

downloading, by a controller, a map comprising an area set as a parking zone from a map data unit for storing a high definition map when an entry of the vehicle to a parking lot is identified;

recognizing, by the controller, an automated valet parking (AVP) start position based on a short-distance lane and stop line recognized by a surround view monitor (SVM) processor, when it is determined that the vehicle has parked at the AVP start position by receiving GPS information or a signal, indicating that the vehicle has parked, from AVP infrastructure installed in the parking lot; and

correcting, by the controller, a position measurement value of the vehicle by performing map matching based on results of a recognition and processing of the front camera processor and the SVM processor and the parking lot map of the map data unit,

wherein in the predicting of the behavior of the vehicle, the controller predicts the behavior of the vehicle through dead reckoning based on the GPS information received from the GPS receiver and a vehicle steering wheel angle, yaw rate and wheel speed received from a vehicle sensor unit, and

wherein in the correcting of the position measurement value, the controller performs the map matching based on lane fusion data in which a long-distance lane recognized by the front camera processor and the short-distance lane and stop line recognized by the SVM processor have been fused, parking lot map data from the map data unit, and vehicle behavior data for each time predicted through dead reckoning.

8. The method of claim 7 , further comprising:

predicting, by the controller, a behavior of the vehicle through dead reckoning when the AVP start position is recognized, and

estimating, by the controller, an AVP initial position of the vehicle by fusing the position measurement value of the vehicle corrected through the map matching and the predicted behavior of the vehicle.

9. The method of claim 7 , wherein in the correcting of the position measurement value, the controller computes a position and rotation correction quantity in which a distance error between sensor data and map data is minimized using iterative closest point (ICP) logic.

10. The method of claim 7 , wherein in the estimating of the AVP initial position, the controller fuses a vehicle pose output as results of the map matching and GPS information of a vehicle position predicted through dead reckoning.

11. The method of claim 10 , further comprising receiving, by the controller, the vehicle position and flags output as the result of the position fusion and performing fail-safe diagnosis,

wherein in the performing of the fail-safe diagnosis, the controller performs the fail-safe diagnosis using a distribution chart configured with estimated positioning results in which positioning

results at past timing have been projected on current timing and positioning results input at current timing.