IP Library › Granted Patent US 11,551,552
Granted Patent B2
US 11,551,552 · App. 16/518,907 · Granted Jan 10, 2023

Distributing processing resources across local and cloud-based systems with respect to autonomous navigation

Inventors: Ashiwan Sivakumar (Pittsburgh, PA); Fan Bai (Ann Arbor, MI); Peter Steenkiste (Pittsburgh, PA)
Assignees: GM GLOBAL TECHNOLOGY OPERATIONS LLC; CARNEGIE MELLON UNIVERSITY
G08G1/096827G05D1/0088G05D1/0212G08G1/056G08G1/22G05D2201/0213
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,551,552
App. No.
16/518,907
Granted
Jan 10, 2023
Kind
B2
Abstract

Embodiments herein include a method executable by a processor coupled to a memory. The processor is local to a vehicle can operable to determine initial location and direction information associated with the vehicle at an origin of a trip request. The processor receives one or more frames captured while the vehicle is traveling along a navigable route relative to the trip request and estimates an execution time for each of one or more computations respective to an analyzing of the one or more frames. The processor, also, off-loads the one or more computations to processing resources of a cloud-based system that is in communication with the processor of the vehicle in accordance with the corresponding execution times.

Claims (44)

1. A method executable by a processor coupled to a memory, the processor being local to a vehicle, the method comprising:

determining, by the processor, initial location and direction information associated with the vehicle at an origin of a trip request;

receiving, by the processor, one or more frames captured while the vehicle is traveling along a navigable route relative to the trip request;

determining from the one or more frames whether a portion of the navigable route has been previously traveled by the vehicle;

based on the portion of the navigable route having been previously traveled, receiving one or more reference frames associated with the portion of the navigable route, and determining a number of features in common between the one or more frames and the one or more reference frames;

estimating, by the processor, an execution time for each of one or more computations respective to an analyzing of the one or more frames, wherein the execution time is based on the number of features in common; and

off-loading, by the processor, the one or more computations to processing resources of a cloud-based system that is in communication with the processor of the vehicle in accordance with the corresponding execution times.

2. The method of claim 1 , wherein the off-loading of the one or more computations comprises:

detecting a bandwidth of a connection between the cloud-based system and the processor of the vehicle; and

off-loading the one or more computations to the processing resources in accordance with the bandwidth.

3. The method of claim 1 , wherein the analyzing of the one or more frames comprises extracting a feature set on a per frame basis to determine progressive location and direction information associated with the vehicle.

4. The method of claim 1 , wherein the off-loading is adaptive in accordance with the analyzing of the one or more frames.

5. The method of claim 1 , the method further comprising receiving, as an input, the trip request comprising the navigable route from the origin to a destination.

6. The method of claim 1 , the method further comprising determining the initial location and direction information associated with the vehicle based on an analysis of a frame captured at the origin of the trip request.

7. The method of claim 1 , the method further comprising autonomously navigating the vehicle based at least on the one or more computations.

8. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor coupled to a memory, the processor being local to a vehicle, the program instructions executable by the processor to cause operations comprising:

determining initial location and direction information associated with the vehicle at an origin of a trip request;

receiving one or more frames captured while the vehicle is traveling along a navigable route relative to the trip request;

determining from the one or more frames whether a portion of the navigable route has been previously traveled by the vehicle;

based on the portion of the navigable route having been previously traveled, receiving one or more reference frames associated with the portion of the navigable route, and determining a number of features in common between the one or more frames and the one or more reference frames;

estimating an execution time for each of one or more computations respective to an analyzing of the one or more frames, wherein the execution time is based on the number of features in common; and

off-loading the one or more computations to processing resources of a cloud-based system that is in communication with the processor of the vehicle in accordance with the corresponding execution times.

9. The computer program product of claim 8 , wherein the off-loading of the one or more computations comprises:

detecting a bandwidth of a connection between the cloud-based system and the processor of the vehicle; and

off-loading the one or more computations to the processing resources in accordance with the bandwidth.

10. The computer program product of claim 8 , wherein the analyzing of the one or more frames comprises extracting a feature set on a per frame basis to determine progressive location and direction information associated with the vehicle.

11. The computer program product of claim 8 , wherein the off-loading is adaptive in accordance with the analyzing of the one or more frames.

12. The computer program product of claim 8 , the program instructions executable by the processor to cause operations comprising receiving, as an input, the trip request comprising the navigable route from the origin to a destination.

13. The computer program product of claim 8 , the program instructions executable by the processor to cause operations comprising determining the initial location and direction information associated with the vehicle based on an analysis of a frame captured at the origin of the trip request.

14. The computer program product of claim 8 , the program instructions executable by the processor to cause operations comprising autonomously navigating the vehicle based at least on the one or more computations.

15. A system comprising a processor and a memory storing program instructions thereon, the processor being local to a vehicle, the program instructions executable by the processor to cause the system to perform:

determining initial location and direction information associated with the vehicle at an origin of a trip request;

receiving one or more frames captured while the vehicle is traveling along a navigable route relative to the trip request;

determining from the one or more frames whether a portion of the navigable route has been previously traveled by the vehicle;

based on the portion of the navigable route having been previously traveled, receiving one or more reference frames associated with the portion of the navigable route, and determining a number of features in common between the one or more frames and the one or more reference frames;

estimating an execution time for each of one or more computations respective to an analyzing of the one or more frames, wherein the execution time is based on the number of features in common; and

off-loading the one or more computations to processing resources of a cloud-based system that is in communication with the processor of the vehicle in accordance with the corresponding execution times.

16. The system of claim 15 , wherein the off-loading of the one or more computations comprises:

detecting a bandwidth of a connection between the cloud-based system and the processor of the vehicle; and

off-loading the one or more computations to the processing resources in accordance with the bandwidth.

17. The system of claim 15 , wherein the analyzing of the one or more frames comprises extracting a feature set on a per frame basis to determine progressive location and direction information associated with the vehicle.

18. The system of claim 15 , wherein the off-loading is adaptive in accordance with the analyzing of the one or more frames.

19. The system of claim 15 , the program instructions executable by the processor to cause the system to perform receiving, as an input, the trip request comprising the navigable route from the origin to a destination.

20. The system of claim 15 , the program instructions executable by the processor to cause the system to perform determining the initial location and direction information associated with the vehicle based on an analysis of a frame captured at the origin of the trip request.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 6, 2022
From: BAI, FAN
To: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Reel/Frame 058562/0970 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 30, 2019
From: BAI, FAN
To: GM GLOBAL TECHNOLOGY OPERATIONS LLC
Reel/Frame 049906/0177 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 30, 2019
From: SIVAKUMAR, ASHIWAN; STEENKISTE, PETER
To: CARNEGIE MELLON UNIVERSITY
Reel/Frame 049906/0319 →
Continuity (2)
Provisional Application 62711932 · Jul 30, 2018
Related Publication 20200035099A1 · Jan 30, 2020