Combined radar and GPS localization system

• US 9,562,778 B2
• Filed: 06/03/2011
• Issued: 02/07/2017
• Est. Priority Date: 06/03/2011
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: DuHadway, Charles, Becker, Jan, Pitzer, Benjamin
• Primary Examiner(s): SMITH, ISAAC G
• Application Number:
  US13/153,137
• Publication Number:
  US 20120310504A1
• Time in Patent Office: 2,076 Days
• Field of Search: 701/117, 701/93, 701/24, 701/26, 701/300, 701/36, 701/408, 701/411, 701/414, 701/432, 701/438, 701/445, 701/446, 701/532, 701/533, 340/435, 340/436, 340/438, 340/904, 342/173, 342/357.23, 342/357.25, 342/357.28, 342/357.32, 342/70, 382/104
• US Class Current: 1/1
• CPC Class Codes: G01C 21/28 with correlation of data from several navigational instruments
• CPC Class Codes: G01S 13/86 Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
• CPC Class Codes: G01S 19/45 by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
• CPC Class Codes: G01S 5/0278 involving statistical or probabilistic considerations G01S5/0252, G01S5/0294 take precedence

Abstract

A localization system within a vehicle in one embodiment includes a global position system (GPS) receiver, a radar sensor, a data storage device including program instructions stored therein, a symbolic map stored within the data storage device, and a controller operatively coupled to the data storage device, the GPS receiver, and the radar sensor, the controller configured to execute the program instructions to analyze data from the GPS receiver, data from the radar sensor, and data from the stored symbolic map, and determine a probabilistic vehicle location based upon the analysis.

Claims

1. A localization system within a vehicle comprising:

a global position system (GPS) receiver;

a radar sensor;

a data storage device including program instructions stored therein;

a symbolic map stored within the data storage device; and

a controller operatively coupled to the data storage device, the GPS receiver, and the radar sensor, the controller configured to execute the program instructions to

analyze data from the GPS receiver, data from the radar sensor, and data from the stored symbolic map, and

determine a probabilistic vehicle location based upon the analysis,

wherein the symbolic map comprises a map with lane-specific detail, and

the probabilistic vehicle location is a location within an error envelope of a calculated GPS location which is most likely to be the actual vehicle location.

2. The system of claim 1, wherein analyzing the data from the GPS receiver, data from the radar sensor, and data from the stored symbolic map comprises:

generating a list of possible vehicle locations based upon the data from the GPS receiver, and determining a probabilistic vehicle location comprises;

estimating, for each of the possible vehicle locations, an actual location probability.

3. The system of claim 2, wherein analyzing the data from the GPS receiver, data from the radar sensor, and data from the stored symbolic map comprises:

determining a velocity for each of a plurality of objects detected by the radar; and

classifying each of the plurality of objects detected by the radar based upon the determined velocity.

4. The system of claim 3, wherein classifying each of the plurality of objects comprises:

classifying each of the plurality of objects detected by the radar based upon the determined velocity as static or dynamic.

5. The system of claim 4, wherein determining a probabilistic vehicle location comprises:

determining, for each of the possible vehicle locations, a respective dynamic object alignment score for each of the plurality of objects classified as dynamic; and

determining, for each of the possible vehicle locations, a respective static object alignment score for each of the plurality of objects classified as static.

6. The system of claim 5, wherein:

the respective dynamic object alignment score is based upon a projected location of a respective one of the plurality of objects classified as dynamic with respect to a first presumed center of a lane; and

the respective static object alignment score is based upon a projected location of a respective one of the plurality of objects classified as static with respect to a second presumed center of a lane.

7. The system of claim 3, wherein determining a probabilistic vehicle location comprises:

determining, for each of the possible vehicle locations, a respective object alignment score for each of the plurality of objects.

8. The system of claim 7, wherein:

the respective object alignment score is based upon a projected location of a respective one of the plurality of objects with respect to a presumed center of a lane.

9. The system of claim 1, wherein the controller is further configured to execute the program instructions to generate a lane-specific navigation instruction based upon the determined probabilistic vehicle location.

10. The system of claim 1, wherein the controller is further configured to execute the program instructions to generate a lane-specific lane departure warning based upon the determined probabilistic vehicle location.

11. The system of claim 1, wherein the controller is further configured to execute the program instructions to generate an adaptive cruise instruction based upon the determined probabilistic vehicle location.

12. A method of localizing a vehicle comprising:

determining a global position system (GPS) location;

obtaining radar sensor data associated with a plurality of radar detected objects;

defining a first possible vehicle location with reference to a symbolic map based on the determined GPS location;

projecting a first location of the plurality of radar detected objects with reference to the symbolic map based on the first possible vehicle location;

analyzing the projected first location of the plurality of radar detected objects; and

determining a probabilistic vehicle location based upon the analysis of the projected first location, wherein

the symbolic map comprises a map with lane-specific detail, and

the probabilistic vehicle location is a location within an error envelope of a calculated GPS location which is most likely to be the actual vehicle location.

13. The method of claim 12, further comprising:

defining a second possible vehicle location with reference to the symbolic map based on the determined GPS location;

projecting a second location of the plurality of radar detected objects with reference to the symbolic map based on the second possible vehicle location;

analyzing the projected second location of the plurality of radar detected objects; and

determining the probabilistic vehicle location based upon the analysis of the projected second location.

14. The method of claim 13, further comprising:

determining a velocity for each of the plurality of radar detected objects; and

classifying each of the plurality of radar detected objects based upon the determined velocity.

15. The method of claim 14, wherein classifying each of the plurality of radar detected objects comprises:

classifying each of the plurality of radar detected objects based upon the determined velocity as static or dynamic.

16. The method of claim 15, wherein determining the probabilistic vehicle location based upon the analysis of the projected first location comprises:

determining a respective dynamic object alignment score for each of the plurality of radar detected objects classified as dynamic; and

determining a respective static object alignment score for each of the plurality of radar detected objects classified as static.

17. The method of claim 16, wherein:

the respective dynamic object alignment score is based upon a projected location of a respective one of the plurality of radar detected objects classified as dynamic with respect to a first presumed center of a lane; and

the respective static object alignment score is based upon a projected location of a respective one of the plurality of radar detected objects classified as static with respect to a second presumed center of a lane.

18. The method of claim 14, wherein determining the probabilistic vehicle location based upon the analysis of the projected first location comprises:

determining a respective object alignment score for each of the plurality of radar detected objects.

19. The method of claim 18, wherein:

the respective object alignment score is based upon a projected location of the respective one of the plurality of radar detected objects with respect to a presumed center of a lane.