Local vector map

Patent metadata

Field	Value
Publication number	US-12449273-B2
Application number	US-202218072117-A
Country	US
Kind code	B2
Filing date	Nov 30, 2022
Priority date	Nov 30, 2022
Publication date	Oct 21, 2025
Grant date	Oct 21, 2025

Abstract

Disclosed herein are system, method, and computer program product aspects for enabling providing map updates to an autonomous vehicle (AV). The system can has four features that can ( 1 ) provide live map updates, ( 2 ) provide a mechanism to optimize map updates, ( 3 ) utilize AV sensors to provide local map updates and integrate into the broader map update system, and ( 4 ) provide a mechanism to provide low latency updates.

First claim

What is claimed is:

1. A computer implemented method comprising:
generating, by one or more computing devices of an autonomous vehicle (AV), a local map update document for a map zone based on AV sensor data indicating road conditions of the map zone, wherein the local map update document is generated using a Cereal binary serialization library;
receiving, by the one or more computing devices, a map update document for the map zone, wherein the map update document contains attributes of the map zone;
applying, by the one or more computing devices, more restrictive of the data in the local map update document or the attributes in the map update document to a base map of the AV to generate an updated map based on a conflict between the data and the attributes; and
transmitting, by the one or more computing devices, the updated map to one or more downstream modules of the AV configured to use the updated map to operate the AV based on the more restrictive of the data in the local map update document or the attributes in the map update document.

2. The method of claim 1 , further comprising when no conflict is found, applying, by the one or more computing devices, the data in the local map update document and the attributes in the map update document to the base map to generate the updated map.

3. The method of claim 1 , wherein the transmitting of the updated map to the one or more downstream modules is done based on a subscription model in which the one or more downstream modules subscribe to map client tasks that are configured to push the updated map to the one or more downstream modules when the updated map is generated.

4. The method of claim 3 , further comprising transmitting the updated map to the one or more downstream modules in real-time after the updated map is generated.

5. The method of claim 3 , further comprising transmitting the updated map to the one or more downstream modules based on a scheduled time interval.

6. The method of claim 1 , further comprising updating, by the one or more computing devices, the local map update document in real-time while the AV is operating.

7. A non-transitory computer readable medium including instructions for causing a computing system to perform operations comprising:
generating, by one or more computing devices of an autonomous vehicle (AV), a local map update document for a map zone based on AV sensor data indicating road conditions of the map zone, wherein the local map update document is generated using a Cereal binary serialization library;
receiving, by the one or more computing devices, a map update document for the map zone, wherein the map update document contains attributes of the map zone;
applying, by the one or more computing devices, more restrictive of the data in the local map update document or the attributes in the map update document to a base map of the AV to generate an updated map based on a conflict between the data and the attributes; and
transmitting, by the one or more computing devices, the updated map to one or more downstream modules of the AV configured to use the updated map to operate the AV based on the more restrictive of the data in the local map update document or the attributes in the map update document.

8. The non-transitory computer readable medium of claim 7 , wherein the operations further comprise when no conflict is found, applying, by the one or more computing devices, the data in the local map update document and the attributes in the map update document to the base map to generate the updated map.

9. The non-transitory computer readable medium of claim 7 , wherein the transmitting of the updated map to the one or more downstream modules is done based on a subscription model in which the one or more downstream modules subscribe to map client tasks that are configured to push the updated map to the one or more downstream modules when the updated map is generated.

10. The non-transitory computer readable medium of claim 9 , wherein the operations further comprise transmitting the updated map to the one or more downstream modules in real-time after the updated map is generated.

11. The non-transitory computer readable medium of claim 9 , wherein the operations further comprise transmitting the updated map to the one or more downstream modules based on a scheduled time interval.

12. The non-transitory computer readable medium of claim 7 , wherein the operations further updating, by the one or more computing devices, the local map update document in real-time while the AV is operating.

13. A computing system comprising:
a memory storing instructions;
one or more processors of an autonomous vehicle (AV), coupled to the memory, configured to process the stored instructions to:
generate a local map update document for a map zone based on AV sensor data indicating road conditions of the map zone, wherein the local map update document is generated using a Cereal binary serialization library;
receive a map update document for the map zone, wherein the map update document contains attributes of the map zone;
apply more restrictive of the data in the local map update document or the attributes in the map update document to a base map of the AV to generate an updated map based on a conflict between the data and the attributes; and
transmit the updated map to one or more downstream modules of the AV configured to use the updated map to operate the AV based on the more restrictive of the data in the local map update document or the attributes in the map update document.

14. The computing system of claim 13 , wherein the one or more processors are further configured to, when no conflict is found, apply the data in the local map update document and the attributes in the map update document to the base map to generate the updated map.

15. The computing system of claim 13 , wherein the one or more processors are further configured to transmit the updated map to the one or more downstream modules based on a subscription model in which the one or more downstream modules subscribe to map client tasks that are configured to push the updated map to the one or more downstream modules when the updated map is generated.

16. The computing system of claim 15 , wherein the one or more processors are further configured to transmit the updated map to the one or more downstream modules in real-time after the updated map is generated.

17. The computing system of claim 15 , wherein the one or more processors are further configured to transmit the updated map to the one or more downstream modules based on a scheduled time interval.

18. The computing system of claim 13 , wherein the one or more processors are further configured to update the local map update document in real-time while the AV is operating.

Assignees

• Argo Ai Llc
• Volkswagen Group Of America Invest Llc

Inventors

• Douglas Timothy James

Classifications

• B60W2556/40

  High definition maps · CPC title

• B60W60/0025

  specially adapted for specific operations · CPC title

• B60W60/001

  Planning or execution of driving tasks · CPC title

• G01C21/3837 Primary

  Data obtained from a single source · CPC title