Vehicle localization

Patent metadata

Field	Value
Publication number	US-12049222-B2
Application number	US-202117547465-A
Country	US
Kind code	B2
Filing date	Dec 10, 2021
Priority date	Dec 10, 2021
Publication date	Jul 30, 2024
Grant date	Jul 30, 2024

Abstract

A plurality of localization data sources accessible on a vehicle network in a vehicle can be identified. A plurality of active vehicle applications that request localization data provided by one or more of the localization data sources can be identified. Based on the active vehicle applications, a plurality of the localization data sources to be combined to output a vehicle location can be selected.

First claim

The invention claimed is:

1. A system for a vehicle, comprising:
a network interface connectable to a vehicle network; and
a processor and a memory, the memory storing instructions executable by the processor, including instructions to:
identify a plurality of localization data sources accessible on the vehicle network;
identify a plurality of active vehicle applications that request localization data provided by one or more of the localization data sources; and
select, based on the active vehicle applications, a plurality of the localization data sources to be combined to output a vehicle location;
wherein the instructions to select one or more of the localization data sources include selecting the localization data sources output from a machine learning program that receives as input identifiers for (a) the localization data sources accessible on the vehicle network, and (b) the active applications that request the localization data;
wherein the machine learning program is trained with previously collected localization data from the localization data sources.

2. The system of claim 1 , wherein respective ones of the localization data sources belong to one of a plurality of types of localization data sources.

3. The system of claim 2 , wherein the types of localization data sources include two or more of map data, V2X data, vehicle sensor data, or vehicle location data.

4. The system of claim 2 , wherein the instructions further include instructions to combine the localization data according to the types of localization data sources.

5. The system of claim 4 , wherein the instructions further include instructions to perform a data fusion procedure that receives the combined localization data as input and that outputs the vehicle location.

6. The system of claim 1 , wherein the instructions further include instructions to perform an initialization routine upon an ignition-ON signal on the vehicle network, wherein the initialization routine includes compiling instructions to allow the system to request and receive data from the selected localization data sources.

7. The system of claim 6 , wherein the instructions further include instructions to identify a minimum number of localization data sources needed for the initialization routine.

8. The system of claim 1 , wherein the instructions further include instructions to assign an application priority to respective active vehicle applications based on a vehicle operation that utilizes the respective active vehicle application.

9. The system of claim 8 , wherein the instructions further include instructions to assign data source priorities to respective localization data sources based on the application priority or priorities of one or more active vehicle applications requiring the respective localization data source.

10. The system of claim 1 , wherein the active vehicle applications include at least one of a vehicle human-machine interface (HMI), an Emergency Electronic Brake Light (EEBL), Green Light Optimal Speed Advisory (GLOSA), Global Location Number (GLN), cruise control, lane-keeping assistant, path planning, a toll payment, traffic light 306 information, parking, electric vehicle charging, or collision avoidance.

11. The system of claim 1 , wherein the instructions further include instructions to provide an identification of at least one of the active vehicle applications to a human machine interface (HMI) in the vehicle.

12. A method, comprising:
identifying a plurality of localization data sources accessible on a vehicle network in a vehicle;
identifying a plurality of active vehicle applications that request localization data provided by one or more of the localization data sources;
selecting, based on the active vehicle applications, a plurality of the localization data sources to be combined to output a vehicle location, the localization data sources being output from a machine learning program that receives as input identifiers for (a) the localization data sources accessible on the vehicle network, and (b) the active applications that request the localization data; and
training the machine learning program with previously collected localization data from the localization data sources.

13. The method of claim 12 , wherein respective ones of the localization data sources belong to one of a plurality of types of localization data sources.

14. The method of claim 13 , wherein the types of localization data sources include two or more of map data, V2X data, vehicle sensor data, or vehicle location data.

15. The method of claim 13 , further comprising combining the localization data according to the types of localization data sources.

16. The method of claim 13 , further comprising performing a data fusion procedure that receives the combined localization data as input and that outputs the vehicle location.

17. The method of claim 12 , further comprising assigning an application priority to respective active vehicle applications based on a vehicle operation that utilizes the respective active vehicle application.

18. The method of claim 17 , wherein assigning data source priorities to respective localization data sources is done based on the application priority or priorities of one or more active vehicle applications requiring the respective localization data source.

Assignees

• Ford Global Tech Llc

Inventors

• Bandi Krishna
• Ibrahim Samer
• Knopp Colette
• Tonshal Basavaraj
• Palakonda Sathyanarayana Chary

Classifications

• G06F18/214 Primary

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06F18/25

  Fusion techniques · CPC title

• B60W2554/4041

  Position · CPC title

• H04W4/40

  for vehicles, e.g. vehicle-to-pedestrians [V2P] · CPC title

• H04W4/025

  using location based information parameters · CPC title