Localization technique

Patent metadata

Field	Value
Publication number	US-11035679-B2
Application number	US-201916239952-A
Country	US
Kind code	B2
Filing date	Jan 4, 2019
Priority date	Jan 4, 2019
Publication date	Jun 15, 2021
Grant date	Jun 15, 2021

Abstract

A computer includes a processor and a memory. The memory stores instructions executable by the processor to receive, in a vehicle, object data from an external node, and upon identifying a point, in the received object data, that is within a volume defined based on vehicle position data received from a vehicle sensor, to determine an adjusted vehicle position based on the identified point and the vehicle position data.

First claim

What is claimed is:

1. A computer, comprising a processor and a memory, the memory storing instructions executable by the processor to:
receive object data in a vehicle via wireless communications from an object-detection sensor that is external to the vehicle;
upon identifying a point in the received object data that is within a volume defined using vehicle position data received from a vehicle sensor, determine an adjusted vehicle position by fusing the identified point and the vehicle position data; and
operate the vehicle based on the adjusted vehicle position.

2. The computer of claim 1 , wherein the identified point is a reference point of an object described in the received object data.

3. The computer of claim 1 , wherein the instructions further comprise to determine the volume based at least in part on vehicle dimensions.

4. The computer of claim 1 , wherein a bottom of the volume is centered at a projection of a vehicle reference point on a ground surface determined based on the vehicle position data.

5. The computer of claim 1 , wherein the instructions further comprise to operate the vehicle based on the adjusted vehicle position.

6. The computer of claim 1 , wherein the instructions further comprise to:
filter the vehicle position data by applying a first Kalman filter to the vehicle position data; and
filter position data of the identified point by applying a second Kalman filter to the position data of the point.

7. The computer of claim 1 , wherein the instructions further comprise to operate the vehicle based on the vehicle position data upon determining that the object from the received object data lacks a point within the volume.

8. The computer of claim 1 , wherein the instructions further comprise to identify the point within the volume only upon determining, based on the received object data, that the identified point is a reference point of an object with a type that matches a vehicle type.

9. The computer of claim 1 , wherein the instructions further comprise to identify the point within the volume only upon determining, based on the received object data, that the identified point is a reference point of an object with dimensions that match the dimensions of the vehicle that received the object data.

10. The computer of claim 1 , wherein the instructions further comprise to:
determine the volume with a bottom on a ground surface with predetermined dimensions centered at a projection vehicle position on a ground surface; and
upon identifying an object, from the object data, with a reference point that is within the determined volume, determine the adjusted vehicle position based in part on location coordinates of the object reference point.

11. The computer of claim 1 , wherein the position data includes at least a lateral coordinate, a longitudinal coordinate, an orientation, a lateral speed, a longitudinal speed, and a rotational speed of the vehicle.

12. The computer of claim 1 , wherein the object data further include at least a lateral coordinate, a longitudinal coordinate, an orientation, a lateral speed, a longitudinal speed, and a rotational speed of an object.

13. The computer of claim 1 , wherein the object data include at least one of location coordinates, an orientation, an object type, a speed, a rotational speed, a shape, and dimensions of the object.

14. A computer, comprising a processor and a memory, the memory storing instructions executable by the processor to:
extract, from an object-data set received in a vehicle via wireless communications from an object-detection sensor external to the vehicle, extra-positional data that correlates with vehicle position data;
independently filter the extra-positional and vehicle position data;
fuse the filtered extra-positional and vehicle position data to improve vehicle localization; and then
operate the vehicle based on the fused filtered extra-positional and vehicle position data.

15. The computer of claim 14 , wherein the instructions further comprise to operate the vehicle based on the fused filtered extra-positional and vehicle position data.

16. The computer of claim 14 , wherein the instructions further comprise to:
filter the vehicle position data by applying a first Kalman filter to the vehicle position data; and
filter the extra-positional data that correlates with vehicle position data by applying a second Kalman filter to the extra-positional data that correlates with the vehicle position data.

17. The computer of claim 14 , wherein the instructions further comprise to operate a vehicle based on the vehicle position data upon determining that the extra-positional data from the object-detection sensor external to the vehicle correlates with the vehicle position data.

18. The computer of claim 14 , wherein the extra-positional data include at least one of location coordinates, an orientation, an object type, a speed, a rotational speed, a shape, and dimensions of a vehicle.

19. The computer of claim 14 , wherein the instructions further comprise to extract the extra-positional data that correlates with the vehicle position upon determining, based on the received object-data set, that the extra-positional data describes an object with dimensions that match the dimensions of the vehicle that received the object-data set.

20. A computer, comprising a processor and a memory, the memory storing instructions executable by the processor to:
receive, in a vehicle, object data from an external object-detection sensor; and
upon identifying a point, in the received object data, that is within a volume defined using vehicle position data received from a vehicle sensor, determine an adjusted vehicle position by fusing the identified point and the vehicle position data, wherein the point is identified within the volume only upon determining, based on the received object data, that the identified point is a reference point of an object with dimensions that match the dimensions of the vehicle that received the object data.

Assignees

• Ford Global Tech Llc

Inventors

• Cionca Codrin
• Castorena Martinez Juan Enrique
• Parchami Mostafa

Classifications

• G01C21/30 Primary

  Map- or contour-matching · CPC title

• G06T2207/30244

  Camera pose · CPC title

• G06T2207/30232

  Surveillance · CPC title

• G01S19/45

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

• G01C21/28 Primary

  with correlation of data from several navigational instruments · CPC title