Method and apparatus for managing vehicle's resource in autonomous driving system

Patent metadata

Field	Value
Publication number	US-12175348-B2
Application number	US-202017039476-A
Country	US
Kind code	B2
Filing date	Sep 30, 2020
Priority date	Oct 24, 2019
Publication date	Dec 24, 2024
Grant date	Dec 24, 2024

Abstract

A method for managing a vehicle's resource includes: executing at least one application requiring a resource in a first mode, the at least one application associated with autonomous driving process of the vehicle, obtaining driving route information, obtaining, from a position data generation device disposed at the vehicle, location information providing a current location of the vehicle, predicting resource utilization expected to be required in the first mode by using the driving route information and the location information, and switching from the first mode executing the at least one application to a second mode, wherein the at least one application is executed in the second mode requiring less resources than being executed in the first mode based on the predicted resource utilization exceeding a first threshold.

First claim

What is claimed is:

1. A method for managing a resource in a vehicle, comprising:
executing at least one application requiring a resource in a first mode, the at least one application associated with an autonomous driving process of the vehicle;
obtaining driving route information;
obtaining, from a position data generation device disposed at the vehicle, location information providing a current location of the vehicle;
predicting resource utilization expected to be required in the first mode by using the driving route information and the location information;
determining a specific point for switching from the first mode executing the at least one application to a second mode;
receiving, from a server, a container module including application data of the second mode that includes information related to the at least one application to be operated in the vehicle; and
installing the received container module,
wherein the at least one application is executed in the second mode requiring less resources than being executed in the first mode.

2. The method of claim 1 , wherein predicting resource utilization includes:
applying the driving route information and the location information to an artificial neural network (ANN) model; and
predicting the resource utilization from an output value of the artificial neural network model.

3. The method of claim 2 , wherein predicting resource utilization includes:
inputting the driving route information and the location information into the artificial neural network model; and
predicting resource utilization related to the output value of the artificial neural network model.

4. The method of claim 3 , wherein inputting the driving route information into the artificial neural network model includes:
extracting a feature from the driving route information; and
inputting the extracted feature into the artificial neural network model.

5. The method of claim 4 ,
wherein the extracted feature includes a vector that is extracted from the driving route information based on a pre-trained embedding model, and
wherein the pre-trained embedding model is configured to vectorize the driving route information to an embedding vector related to the driving route information.

6. The method of claim 2 , further comprising:
applying an application usage history of passenger to the artificial neural network model as learning data.

7. The method of claim 1 , wherein the driving route information includes at least one of a driving route to a destination, execution mode information of the at least one application used in the autonomous driving process, a uniformity of a road surface located on the driving route, a curvature of a road, a number of surrounding objects, or a type of the surrounding objects.

8. The method of claim 1 , wherein the at least one application comprises at least one of a navigation application, an object detection application, a voice recognition application, or a multimedia application.

9. The method of claim 1 , wherein the server is configured to search for the application data based on allowable resource information for the vehicle.

10. The method of claim 1 , wherein the server is configured to search for the at least one application including a feature function that is included in the application data.

11. The method of claim 1 , wherein the container module further includes metadata corresponding to a specific function of the vehicle, and
wherein installing the received container module comprises installing the at least one application included in the received container module as an application corresponding to the specific function of the vehicle.

12. The method of claim 1 , further comprising:
determining a value of communication specification based on at least one of a traffic density, speed, or a presence or absence of obstacles,
wherein determining the specific point comprises, based on a determination that the value of communication specification has passed a predetermined threshold, determining a current time as the specific point.

13. The method of claim 1 ,
wherein determining the specific point comprises determining a point at which the resource utilization exceeds a first threshold as the specific point,
wherein installing the received container module comprises switching, based on the vehicle passing the specific point, the execution mode from the first mode executing the at least one application to the second mode.

14. An apparatus for managing a resource in a vehicle, comprising:
a transceiver configured to receive driving route information of the vehicle;
a position data generation device configured to provide location information providing a current location of the vehicle; and
a processor configured to:
execute at least one application requiring a resource in a first mode, the at least one application associated with an autonomous driving process of the vehicle,
predict resource utilization expected to be required in the first mode by using the received driving route information and the provided location information,
determine a specific point for switching from the first mode executing the at least one application to a second mode,
receive, from a server, a container module including application data of the second mode that includes information related to the at least one application to be operated in the vehicle, and
install the received container module,

wherein the at least one application is executed in the second mode requiring less resources than being executed in the first mode.

15. The apparatus of claim 14 , wherein predicting resource utilization includes:
applying the driving route information and the location information to an artificial neural network model, and
predicting the resource utilization from an output value of the artificial neural network model.

16. The apparatus of claim 15 , wherein predicting resource utilization includes:
inputting the driving route information and the location information into the artificial neural network model, and
predicting resource utilization related to the output value of the artificial neural network model.

17. The apparatus of claim 16 , wherein inputting the driving route information into the artificial neural network model includes:
extracting a feature from the driving route information, and
inputting the extracted feature into the artificial neural network model.

18. The apparatus of claim 17 ,
wherein the extracted feature includes a vector that is extracted from the driving route information based on a pre-trained embedding model, and
wherein the pre-trained embedding model is configured to vectorize the driving route information to an embedding vector related to the driving route information.

19. The apparatus of claim 15 , wherein the driving route information includes at least one of a driving route to a destination, execution mode information of the at least one application used in the autonomous driving process, a uniformity of a road surface located on the driving route, a curvature of a road, a number of surrounding objects, or a type of the surrounding objects.

20. The apparatus of claim 14 , wherein the at least one application comprises at least one of a navigation application, an object detection application, a voice recognition application, or a multimedia application.

21. The apparatus of claim 14 , wherein the server is configured to search for the application data based on allowable resource informa

Assignees

• Lg Electronics Inc

Inventors

• Lee Dongkyu
• Park Namyong
• Lee Eunkoo
• Lee Chulhee
• Yoon Taesuk

Classifications

• G06N3/0499

  Feedforward networks · CPC title

• G06N3/092

  Reinforcement learning · CPC title

• G06N3/09

  Supervised learning · CPC title

• B60W2050/0005

  Processor details or data handling, e.g. memory registers or chip architecture · CPC title

• B60W50/082 Primary

  Selecting or switching between different modes of propelling · CPC title