Methods and systems for precise vehicle localization using radar maps

• US 9,194,949 B2
• Filed: 10/20/2011
• Issued: 11/24/2015
• Est. Priority Date: 10/20/2011
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Becker, Jan, Schwindt, Oliver, Kammel, Soeren
• Primary Examiner(s): Nguyen, Kim T
• Application Number:
  US13/277,879
• Publication Number:
  US 20130103298A1
• Time in Patent Office: 1,496 Days
• Field of Search: 701/300, 701/472, 701/468, 701/500, 701/507, 701/514, 701/523, 701/532, 701/540
• US Class Current: 1/1
• CPC Class Codes: G01S 13/86 Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
• CPC Class Codes: G01S 13/89 for mapping or imaging
• CPC Class Codes: G01S 13/895 Side looking radar [SLR]

Abstract

A method for determining a location of a vehicle. The method includes steps of acquiring a plurality of sensor data from a radar sensor associated with the vehicle; obtaining an approximate location of the vehicle using a GPS unit; comparing the sensor data to a database of geo-referenced sensor data; and based on the comparison, determining a location of the vehicle.

Claims

1. A method for determining a location of a vehicle, comprising:

acquiring a plurality of sensor data traces from a radar sensor associated with the vehicle;

obtaining velocity information from the plurality of sensor data traces;

using the velocity information, identifying a portion of the plurality of sensor data traces corresponding to a moving object;

removing the portion of the plurality of sensor data traces corresponding to the moving object from the plurality of sensor data traces;

obtaining an approximate location of the vehicle using a GPS unit;

comparing the sensor data traces to a database of geo-referenced sensor data traces; and

based on the comparison, determining the location of the vehicle.

2. The method of claim 1, wherein comparing the sensor data traces to the database of geo-referenced sensor data traces further comprises identifying a portion of the database corresponding to the approximate location of the vehicle.

3. The method of claim 2, wherein comparing the sensor data traces to the database of geo-referenced sensor data traces comprises fitting the sensor data traces onto the portion of the database.

4. The method of claim 3, wherein fitting the sensor data traces onto the portion of the database comprises fitting the sensor data traces onto the portion of the database using a cross correlation function.

5. The method of claim 1, wherein acquiring the plurality of sensor data traces from the radar sensor comprises acquiring the plurality of sensor data traces from a plurality of radar sensors associated with the vehicle.

6. The method of claim 1, wherein acquiring the plurality of sensor data traces includes additional sensor data traces from at least one of the group consisting of a video imaging system, a laser scanner system, a lidar system, and an inertial measurement unit.

7. The method of claim 1, wherein comparing the sensor data traces to the database of geo-referenced sensor data traces includes comparing a raw waveform received from the radar sensor to a corresponding waveform in the database.

8. The method of claim 1, wherein the sensor data traces are raw data or are formatted similar to raw data.

9. A system for determining a location of a vehicle, comprising:

a vehicle having at least one radar sensor and a GPS unit associated therewith;

a controller in communication with the at least one radar sensor and the GPS unit, the controller configured to

acquire a plurality of sensor data traces from the radar sensor associated with the vehicle;

obtain velocity information from the plurality of sensor data traces;

using the velocity information, identify a portion of the plurality of sensor data traces corresponding to a moving object;

remove the portion of the plurality of sensor data traces corresponding to the moving object from the plurality of sensor data traces;

compare the sensor data traces to a database of geo-referenced sensor data traces; and

based on the comparison, determine the location of the vehicle.

10. The system of claim 9, wherein the controller, in order to compare the sensor data traces to the database of geo-referenced sensor data traces, is further configured to identify a portion of the database corresponding to an approximate location of the vehicle.

11. The system of claim 10, wherein the controller, in order to compare the sensor data traces to the database of geo-referenced sensor data traces, is further configured to fit the sensor data traces onto the portion of the database.

12. The system of claim 11, wherein the controller, in order to fit the sensor data traces onto the portion of the database, is further configured to fit the sensor data traces onto the portion of the database using a cross correlation function.

13. The system of claim 9, wherein the vehicle further has a plurality of radar sensors associated therewith.

14. The system of claim 9, wherein the vehicle further has at least one from the group consisting of a video imaging system, a laser scanner system, a lidar system, and an inertial measurement unit associated therewith and wherein the controller, in order to acquire the plurality of sensor data traces, is further configured to acquire sensor data traces from at least one of the group consisting of the video imaging system, the laser scanner system, the lidar system, and the inertial measurement unit.

15. The system of claim 9, wherein the controller, in order to compare the sensor data traces to the database of geo-referenced sensor data traces, compares a raw waveform received from the radar sensor to a corresponding waveform in the database.

16. The system of claim 9, wherein the sensor data traces are raw data or are formatted similar to raw data.

17. A method for determining a location of a vehicle, comprising:

acquiring a plurality of sensor data traces from a sensor associated with the vehicle;

obtaining velocity information from the plurality of sensor data traces;

using the velocity information, identifying a portion of the plurality of sensor data traces corresponding to a moving object;

removing the portion of the plurality of sensor data traces corresponding to the moving object from the plurality of sensor data traces;

obtaining an approximate location of the vehicle using a GPS unit;

comparing the sensor data traces to a database of geo-referenced sensor data traces; and

based on the comparison, determining the location of the vehicle.