Pose estimation using long range features

• US 9,255,805 B1
• Filed: 05/19/2015
• Issued: 02/09/2016
• Est. Priority Date: 07/08/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ferguson, David I., Silver, David Harrison
• Primary Examiner(s): Trammell, James
• Assistant Examiner(s): SMITH-STEWART, DEMETRA R
• Application Number:
  US14/716,097
• Time in Patent Office: 266 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• CPC Class Codes: G01C 21/26 specially adapted for navigation in a road network
• CPC Class Codes: G01C 21/30 Map- or contour-matching
• CPC Class Codes: G01S 17/875 for determining attitude
• CPC Class Codes: G01S 17/89 for mapping or imaging

Abstract

Aspects of the present disclosure relate to using an object detected at long range to increase the accuracy of a location and heading estimate based on near range information. For example, an autonomous vehicle may use data points collected from a sensor such as a laser to generate an environmental map of environmental features. The environmental map is then compared to pre-stored map data to determine the vehicle'"'"'s geographic location and heading. A second sensor, such as a laser or camera, having a longer range than the first sensor may detect an object outside of the range and field of view of the first sensor. For example, the object may have retroreflective properties which make it identifiable in a camera image or from laser data points. The location of the object is then compared to the pre-stored map data and used to refine the vehicle'"'"'s estimated location and heading.

Claims

1. A method comprising:

receiving data collected by a first sensor while a vehicle is driving on a roadway, the first sensor having a first sensor range;

using the received data from the first sensor to generate a map of the vehicle'"'"'s environment within the first sensor range;

estimating, by a processor, the vehicle'"'"'s geographic location and heading by comparing the generated map to a stored map identifying the geographic locations of objects including reference objects having particular retroreflective, brightness, or intensity characteristics;

receiving data collected by a second sensor while the vehicle is driving on the roadway, the second sensor having a second sensor range greater than the first sensor range;

identifying a reference object having a particular retroreflective, brightness, or intensity characteristic from the data collected by the second sensor outside of the first sensor range;

correlating the identified reference object to a reference object of the stored map based on the particular retroreflective, brightness, or intensity characteristic; and

using the correlation to refine the estimated heading of the vehicle.

2. The method of claim 1, wherein

the estimated geographic location includes at least one of (1) latitude, longitude and altitude coordinates and (2) Coordinated Universal Time coordinates.

3. The method of claim 1, further comprising using the correlation to refine the estimated geographic location of the vehicle.

4. The method of claim 1, wherein the first sensor is a laser and the second sensor is a different laser or a camera.

5. The method of claim 1, wherein estimating the vehicle'"'"'s geographic location and heading is further based on a previous geographic location and heading estimate.

6. A method of claim 1, wherein the first sensor and the second sensor are the same sensor.

7. A method comprising:

generating, by one or more processors, a map of an environment of a vehicle using a first data set collected from within a sensor range;

estimating, by the one or more processors, a heading of the vehicle relative to objects in the generated map, each object having a geographic location correlated to a known geographic location of a first data reference object in a stored map, the stored map identifying known geographic locations and particular retroreflective, brightness, or intensity characteristics of a plurality of reference objects;

identifying, by the one or more processors, a second data reference object having a particular retroreflective, brightness, or intensity characteristic from a second data set collected from outside of the sensor range;

determining, by the one or more processors, a geographic location of the identified second data reference object by correlating the identified second data reference object to a reference object of the stored map based on the particular retroreflective, brightness, or intensity characteristic, the reference object of the stored map having a known geographic location; and

updating, by the one or more processors, the estimated heading of the vehicle using the geographic location of the identified second data reference.

8. The method of claim 7, wherein the first data set is collected by a first sensor and the second data set is collected by a second sensor.

9. The method of claim 7, wherein the identified second data reference object is one of a plurality of second data reference objects from the second data set that is farthest from an estimated location of the vehicle.

10. The method of claim 7, wherein updating the estimated heading of the vehicle further uses at least one of a previously estimated heading of the vehicle, previously determined geographic location of objects, and previously determined geographic location of second data reference objects.

11. The method of claim 7, wherein the first data set and the second data set are collected by one sensor.

12. The method of claim 11, wherein generating the map of the environment of the vehicle further comprises applying a first processing technique to the first data set.

13. The method of claim 12, wherein identifying a second data reference object further comprises applying a second processing technique to the second data set, the second processing technique being different from the first processing technique.

14. The method of claim 11, wherein the sensor is a laser.

15. The method of claim 7, further comprising:

estimating, by the one or more processors, a location of the vehicle relative to the objects in the generated map; and

updating, by the one or more processors, the estimated location of the vehicle using the geographic location of the identified second data reference.

20. The method of claim 7, wherein the first data set and the second data set are collected by one sensor.

16. A system comprising:

one or more sensors configured to collect data while a vehicle is driving on a roadway;

a memory storing a map identifying geographic locations and particular retroreflective, brightness, or intensity characteristics of a plurality of reference objects; and

one or more processors configured to;

generate a map of an environment of a vehicle using a first data set collected from within a sensor range;

estimate a heading of the vehicle relative to objects in the generated map, each object having a geographic location correlated to a known geographic location of a first data reference object in the stored map;

identify one or more second data reference objects from a second data set collected from outside of the sensor range, each second data reference object having a particular retroreflective, brightness, or intensity characteristic;

determine a geographic location of at least one identified second data reference object by correlating each at least one second data reference object with a reference object of the stored map based on the particular retroreflective, brightness, or intensity characteristic, the reference object of the stored map having a known geographic location; and

update the estimated heading of the vehicle using the geographic location of each at least one identified second data reference.

17. The system of claim 16, wherein the first data set is collected by a first sensor and the second data set is collected by a second sensor.

18. The method of claim 16, wherein the at least one identified second data reference object includes a first reference object that is farthest from an estimated location of the vehicle.

19. The method of claim 17, wherein the at least one identified second data reference object further includes a second reference object that has a different bearing to the vehicle than the first reference object.