# US 11,440,537 B2 · Apparatus and method for estimating position in automated valet parking system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,440,537 B2
- Document ID: US11440537B2
- Status: Granted
- Kind: B2
- Application number: 16/810,669
- Filed: 2020-03-05
- Published: 2020-09-24
- Granted: 2022-09-13
- Earliest claimed: 2019-03-19
- Assignees: Hyundai Mobis Co., Ltd.
- Applicants: Hyundai Mobis Co., Ltd.
- Inventors: Dong Wook Kim
- Web page: https://patentgrep.com/patent/US11440537B2

## CPC

- G01C 21/005: {with correlation of navigation data from several sources, e.g. map or contour matching (G01C21/30 takes precedence)}
- B60W 30/06: Automatic manoeuvring for parking
- B60W 30/181: {Preparing for stopping}
- B60W 40/105: Speed
- B60W 40/114: Yaw movement
- B60W 50/0097: {Predicting future conditions}
- B60W 50/0205: {Diagnosing or detecting failures; Failure detection models}
- B60W 50/14: Means for informing the driver, warning the driver or prompting a driver intervention
- G01C 21/165: {combined with non-inertial navigation instruments}
- G01C 21/1656: {with passive imaging devices, e.g. cameras}
- G01C 21/30: Map- or contour-matching
- G06F 18/254: {of classification results, e.g. of results related to same input data}
- G06V 10/809: {of classification results, e.g. where the classifiers operate on the same input data}
- G06V 20/586: {of parking space}
- G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road}
- B60W 2050/0215: {Sensor drifts or sensor failures}
- B60W 2520/04: Vehicle stop
- B60W 2520/14: Yaw
- B60W 2520/28: Wheel speed
- B60W 2540/18: Steering angle
- B60W 2552/53: Road markings, e.g. lane marker or crosswalk
- B60W 2556/40: High definition maps
- G01C 21/206: {specially adapted for indoor navigation}
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An apparatus for estimating a position in an automated valet parking system includes a front camera processor processing a front image of a vehicle, a surround view monitor (SVM) processor recognizing a short-distance lane and stop line by processing a surround view image of the vehicle, a map data unit storing a high definition map, and a controller downloading a map including an area set as a parking zone from the map data unit when the entry of the vehicle to a parking lot is identified and correcting a position measurement value of the vehicle by performing map matching based on results of the recognition and processing of the front camera processor and SVM processor and the parking lot map of the map data unit when an automated valet parking start position is recognized based on the recognized short-distance lane and stop line.

## Claims

### Claim 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.

### Claim 2 (depends on 1)

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.

### Claim 3 (depends on 1)

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.

### Claim 4 (depends on 1)

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.

### Claim 5 (depends on 4)

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.

### Claim 6 (depends on 4)

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.

### Claim 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.

### Claim 8 (depends on 7)

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.

### Claim 9 (depends on 7)

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.

### Claim 10 (depends on 7)

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.

### Claim 11 (depends on 10)

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.