Self-correcting vehicle localization

Patent metadata

Field	Value
Publication number	US-11604288-B2
Application number	US-201916678674-A
Country	US
Kind code	B2
Filing date	Nov 8, 2019
Priority date	Nov 8, 2019
Publication date	Mar 14, 2023
Grant date	Mar 14, 2023

Abstract

A computer is programmed to determine a localization of a first vehicle, including location coordinates and an orientation of the first vehicle, based on first vehicle sensor data, and to wirelessly receive localizations of respective second vehicles, wherein a first vehicle field of view at least partially overlaps respective fields of view of each of the second vehicles. The computer is programmed to determine pair-wise localizations for respective pairs of the first vehicle and one of the second vehicles, wherein each of the pair-wise localizations defines a localization of the first vehicle relative to a global coordinate system based on a (a) relative localization of the first vehicle with reference to the respective second vehicle and (b) a second vehicle localization relative to the global coordinate system, and to determine an adjusted localization for the first vehicle that has a minimized sum of distances to the pair-wise localizations.

First claim

What is claimed is:

1. A computer comprising a processor and a memory, the memory storing instructions executable by the processor to:
determine a localization of a first vehicle, including location coordinates and an orientation of the first vehicle, based on first vehicle sensor data;
wirelessly receive localizations of respective second vehicles, wherein a first vehicle field of view at least partially overlaps respective fields of view of each of the second vehicles;
determine pair-wise localizations for respective pairs of the first vehicle and one of the second vehicles, wherein each of the pair-wise localizations defines a localization of the first vehicle relative to a global coordinate system based on a (a) relative localization of the first vehicle with reference to the respective second vehicle and (b) a second vehicle localization relative to the global coordinate system;
determine an adjusted localization for the first vehicle that has a minimized sum of distances to the pair-wise localizations; and
operate the vehicle according to the adjusted localization.

2. The computer of claim 1 , wherein the sensor data is from one or more of a GPS sensor, LIDAR sensor, camera sensor, or visual odometer.

3. The computer of claim 1 , wherein the second vehicles include respective second computers, each programmed to determine the localization of the second vehicle based on data received from one or more sensors in the respective second vehicle.

4. The computer of claim 1 , wherein the instructions further include instructions to compute each of the one or more pair-wise localization for the first vehicle by:
determining a relative localization of the first vehicle with respect to each respective second vehicle, each relative localization including a relative pose and relative location coordinates with reference to the respective second vehicle based on data received wirelessly from a second vehicle computer;
determining the second vehicle localization based on data received from a sensor in the respective second vehicle; and
determining the pair-wise localization of the first vehicle relative to the global coordinate system based on the second vehicle localization and the relative localization of the first vehicle.

5. The computer of claim 4 , wherein the second vehicle localization includes a second vehicle pose with reference to the global coordinate system and a second vehicle location with reference to the global coordinate system.

6. The computer of claim 5 , wherein the instructions further include instructions to determine a pair-wise pose of the first vehicle based on the relative pose of the first vehicle and the second vehicle pose.

7. The computer of claim 1 , wherein the instructions further include instructions to compute each of the pair-wise localizations by minimizing distances between representations of the area in an objective function.

8. The computer of claim 7 , wherein the area is a 3D area including overlapping portion of the fields of view of the first vehicle and the second vehicles.

9. The computer of claim 1 , wherein the adjusted localization of the first vehicle includes an adjusted first vehicle pose and an adjusted first vehicle pose, and the instructions further include instructions to:
determine the adjusted first vehicle location by minimizing distances between the pair-wise first vehicle locations; and
determine the adjusted first vehicle pose by minimizing distances between the pair-wise first vehicle poses.

10. A method, comprising:
determining a localization of a first vehicle, including location coordinates and an orientation of the first vehicle, based on first vehicle sensor data;
wirelessly receiving localizations of respective second vehicles, wherein a first vehicle field of view at least partially overlaps respective fields of view of each of the second vehicles;
determining pair-wise localizations for respective pairs of the first vehicle and one of the second vehicles, wherein each of the pair-wise localizations defines a localization of the first vehicle relative to a global coordinate system based on a (a) relative localization of the first vehicle with reference to the respective second vehicle and (b) a second vehicle localization relative to the global coordinate system;
determining an adjusted localization for the first vehicle that has a minimized sum of distances to the pair-wise localizations; and
operating the vehicle according to the adjusted localization.

11. The method of claim 10 , wherein the sensor data is from one or more of a GPS sensor, LIDAR sensor, camera sensor, or visual odometer.

12. The method of claim 10 , further comprising determining, in a second computer in each of the second vehicles, the localization of the second vehicle based on data received from one or more sensors in the respective second vehicle.

13. The method of claim 10 , wherein computing each of the one or more pair-wise localization for the first vehicle further includes:
determining a relative localization of the first vehicle with respect to each respective second vehicle, each relative localization including a relative pose and relative location coordinates with reference to the respective second vehicle based on data received wirelessly from a second vehicle computer;
determining the second vehicle localization based on data received from a sensor in the respective second vehicle; and
determining the pair-wise localization of the first vehicle relative to the global coordinate system based on the second vehicle localization and the relative localization of the first vehicle.

14. The method of claim 13 , wherein the second vehicle localization includes a second vehicle pose with reference to the global coordinate system and a second vehicle location with reference to the global coordinate system.

15. The method of claim 14 , further comprising determining a pair-wise pose of the first vehicle based on the relative pose of the first vehicle and the second vehicle pose.

16. The method of claim 10 , further comprising computing each of the pair-wise localizations by minimizing distances between representations of the area in an objective function.

17. The method of claim 16 , wherein the area is a 3D area including overlapping portion of the fields of view of the first vehicle and the second vehicles.

18. The method of claim 10 , further comprising determining an adjusted first vehicle location by minimizing distances between the pair-wise first vehicle locations, wherein the adjusted localization of the first vehicle includes the adjusted first vehicle pose and an adjusted first vehicle pose; and
determining the adjusted first vehicle pose by minimizing distances between the pair-wise first vehicle poses.

Assignees

• Ford Global Tech Llc

Inventors

• Castorena Martinez Juan Enrique
• Cionca Codrin
• Zhang Linjun
• Xu Lu

Classifications

• G01S13/86

  Combinations of radar systems with non-radar systems, e.g. sonar, direction finder · CPC title

• G01S19/45 Primary

  by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title

• G01S17/931 Primary

  of land vehicles · CPC title

• G01S13/874

  Combination of several systems for attitude determination (in general G01C, control of attitude G05D1/49) · CPC title