IP Library › Granted Patent US 12,455,562
Granted Patent B2
US 12,455,562 · App. 17/716,697 · Granted Oct 28, 2025

Self-maintaining autonomous vehicle procedure

Inventors: Xuefeng Wang (Cupertino, CA); Joseph Thibeault (San Francisco, CA); Jose Arturo Covarrubias Reynoso (South San Francisco, CA); Michael Magnoli (San Francisco, CA); Thomas Bachant (New York, NY); Nadav Ullman (New York, NY); Paul Garcia (Lima, PE); Jake McCloskey (New York, NY); Maik Duwensee (San Jose, CA)
Assignee: GM CRUISE HOLDINGS LLC
G05B23/0283B60W50/0205B60W50/029B60W60/00186G05B23/0254G06Q10/20B60W2050/0215B60W2050/0292
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 12,455,562
App. No.
17/716,697
Granted
Oct 28, 2025
Kind
B2
Abstract

Aspects of the disclosed technology encompass solutions for automatically managing autonomous vehicle (AV) operating and maintenance tasks, such as implementing an alternative operating mode or ordering replacement parts for an AV components. In some aspects, a process of the disclosed technology can include steps for receiving diagnostic data corresponding with an AV component, determining an estimated life cycle of the AV component, and determining whether to generate an action to implement an alternative operating mode or an order request for one or more replacement parts of the AV component, based on the estimated life cycle of the AV component. Systems and machine-readable media are also provided.

Claims (57)

1. An apparatus for managing autonomous vehicle (AV) systems, the apparatus comprising:

at least one memory; and

at least one processor coupled to the at least one memory, the at least one processor configured to:

receive, at volumes and in a variety to electronically replicate a dynamic environment, real time sensor data from one or more sensors of an AV that uses some or all of the real time sensor data to self-navigate through the dynamic environment without a human driver;

extract from the real time sensor data a real time data stream comprising first diagnostic data corresponding with an AV component, wherein the AV component is associated with an AV propulsion system, an AV braking system, an AV navigation system, a camera, a Light Detection and Ranging (LiDAR) sensor, a radar sensor, or a combination thereof;

determine, based on the first diagnostic data, a confidence estimate for the first diagnostic data corresponding with the AV component;

determine, based on the first diagnostic data, an estimated life cycle of the AV component;

determine whether to generate an action for the AV, based on the estimated life cycle of the AV component, wherein the action comprises adjusting, based on the confidence estimate, one or more weights that correspond with a confidence in the first diagnostic data corresponding with the AV component; and

responsive to a first result of determining whether to generate the action for the AV, instructing the AV to execute the action, wherein the action is configured to address a detected issue with the AV component.

2. The apparatus of claim 1 , wherein:

the real time data stream further comprises second diagnostic data corresponding with the AV component; and

the at least one processor is further configured to update the estimated life cycle for the AV component based on the second diagnostic data.

3. The apparatus of claim 1 , wherein the action further comprises an order request for one or more replacement parts associated with the AV.

4. The apparatus of claim 1 , wherein the action further comprises an instruction for implementing an alternative self-navigating operating mode of the AV, the alternative self-navigating operating mode including a vehicle pullover maneuver within a period of time less than the estimated life cycle of the AV component.

5. The apparatus of claim 1 , wherein the at least one processor is further configured to:

determine that an impending malfunction of the AV component may affect another AV component wherein the action further comprises an instruction for implementing an alternative operating mode for the AV component or an associated component, the alternative operating mode including shutting down the AV component.

6. The apparatus of claim 3 , wherein to determine whether to generate the action the at least one processor is further configured to:

compare the estimated life cycle of the AV component to a pre-determined threshold; and

generate the action to order the one or more replacement parts if the estimated life cycle of the AV component is below the pre-determined threshold.

7. The apparatus of claim 6 , wherein the at least one processor is further configured to:

route the order action-request based on the one or more replacement parts.

8. The apparatus of claim 1 , wherein to determine the estimated life cycle of the AV component, the at least one processor is configured to:

provide the first diagnostic data to a machine-learning model.

9. The apparatus of claim 1 , wherein the at least one processor is further configured to:

determine a potential of increased damage to the AV component from continued use, wherein the action further comprises an instruction for implementing an alternative operating mode for the AV component or an associated component, the alternative operating mode including shutting down the AV component.

10. A computer-implemented method for managing autonomous vehicle (AV) systems, the computer-implemented method comprising using a processor system of an AV to perform processor system operations comprising:

receiving, at volumes and in a variety to electronically replicate a dynamic environment, real time sensor data from one or more sensors of an AV that uses some or all of the real time sensor data to self-navigate through the dynamic environment without a human driver

extracting from the real time sensor data a real time data stream comprising first diagnostic data corresponding with an AV component, wherein the AV component is associated with an AV propulsion system, an AV braking system, an AV navigation system, a camera, a Light Detection and Ranging (LiDAR) sensor, a radar sensor, or a combination thereof;

determining, based on the first diagnostic data, a confidence estimate for the first diagnostic data corresponding with the AV component;

determining, based on the first diagnostic data, an estimated life cycle of the AV component;

determining whether to generate an action for the AV, based on the estimated life cycle of the AV component, wherein the action comprises adjusting, based on the confidence estimate, one or more weights that correspond with a confidence in the first diagnostic data corresponding with the AV component; and

responsive to a first result of determining whether to generate the action for the AV, instructing the AV to execute the action, wherein the action is configured to address a detected issue with the AV component.

11. The computer-implemented method of claim 10 , wherein:

the real time data stream further comprises second diagnostic data corresponding with the AV; and

the processor system operations further comprise updating the estimated life cycle for the AV component based on the second diagnostic data.

12. The computer-implemented method of claim 10 , wherein the action further comprises an order request for one or more replacement parts associated with the AV.

13. The computer-implemented method of claim 12 , wherein determining whether to generate the action further comprises:

comparing the estimated life cycle of the AV component to a pre-determined threshold; and

generating the action to order the one or more replacement parts if the estimated life cycle of the AV component is below the pre-determined threshold.

14. The computer-implemented method of claim 13 , wherein the processor operations further comprise:

routing the order action-request based on the one or more replacement parts.

15. The computer-implemented method of claim 10 , wherein the action further comprises an instruction for implementing an alternative self-navigating operating mode of the AV, the alternative self-navigating operating mode including a vehicle pullover maneuver within a period of time less than the estimated life cycle of the AV component.

16. The computer-implemented method of claim 10 , the processor system operations further comprise:

determining that an impending malfunction of the AV component may affect another AV component wherein the action further comprises an instruction for implementing an alternative operating mode for the AV component or an associated component, the alternative operating mode including shutting down the AV component.

17. The computer-implemented method of claim 10 , wherein determining the estimated life cycle of the AV component further comprises:

providing the first diagnostic data to a machine-learning model.

18. The computer-implemented method of claim 10 , wherein the processor system operations further comprise:

determining a potential of increased damage to the AV component from continued use, wherein the action further comprises an instruction for implementing an alternative operating mode for the AV component or an associated component, the alternative operating mode including shutting down the AV component.

19. A non-transitory computer-readable storage medium comprising at least one instruction for causing a computer or processor to:

receive, at volumes and in a variety to electronically replicate a dynamic environment, real time sensor data from one or more sensors of an AV that uses some or all of the real time sensor data to self-navigate through the dynamic environment without a human driver;

extract from the real time sensor data a real time data stream comprising first diagnostic data corresponding with an AV component, wherein the AV component is associated with an AV propulsion system, an AV braking system, an AV navigation system, a camera, a Light Detection and Ranging (LiDAR) sensor, a radar sensor, or a combination thereof

determine, based on the first diagnostic data, a confidence estimate for the first diagnostic data corresponding with the AV component;

determine, based on the first diagnostic data, an estimated life cycle of the AV component;

determine whether to generate an action for the AV, based on the estimated life cycle of the AV component, wherein the action comprises adjusting, based on the confidence estimate, one or more weights that correspond with a confidence in the first diagnostic data corresponding with the AV component; and

responsive to a first result of determining whether to generate the action for the AV, instructing the AV to execute the action, wherein the action is configured to address a detected issue with the AV component.

20. The non-transitory computer-readable storage medium of claim 19 , the at least one instruction further causing the computer or processor to:

determine a potential of increased damage to the AV component from continued use, wherein the action further comprises an instruction for implementing an alternative operating mode for the AV component or an associated component, the alternative operating mode including shutting down the AV component.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 8, 2022
From: WANG, XUEFENG; THIBEAULT, JOSEPH; COVARRUBIAS REYNOSO, JOSE ARTURO; MAGNOLI, MICHAEL; BACHANT, THOMAS; ULLMAN, NADAV; GARCIA, PAUL; MCCLOSKEY, JAKE; DUWENSEE, MAIK
To: GM CRUISE HOLDINGS LLC
Reel/Frame 059549/0799 →
Continuity (2)
Continuation In Part 17155921 · Jan 22, 2021
Related Publication 20220236729A1 · Jul 28, 2022
References Cited (24)
US 11614735B1 · Poeppel et al. · 2023 [cited by applicant]
US 20140074345A1 · Gabay et al. · 2014 [cited by applicant]
US 20170123421A1 · Kentley et al. · 2017 [cited by applicant]
US 20170278312A1 · Minster · 2017 [cited by examiner]
US 20180136651A1 · Levinson et al. · 2018 [cited by applicant]
US 20180164814A1 · Poeppel et al. · 2018 [cited by applicant]
US 20180276910A1 · Pitt et al. · 2018 [cited by applicant]
US 20180315260A1 · Anthony · 2018 [cited by applicant]
US 20180322775A1 · Chase et al. · 2018 [cited by applicant]
US 20190129789A1 · Koay et al. · 2019 [cited by applicant]
US 20190184997A1 · Zheng et al. · 2019 [cited by applicant]
US 20190197798A1 · Abari et al. · 2019 [cited by applicant]
US 20190204097A1 · Starns · 2019 [cited by applicant]
US 20190235487A1 · Zhao et al. · 2019 [cited by applicant]
US 20190258251A1 · Ditty · 2019 [cited by examiner]
US 20190378350A1 · DeRouen et al. · 2019 [cited by applicant]
US 20200184278A1 · Zadeh · 2020 [cited by examiner]
US 20210063162A1 · Moskowitz · 2021 [cited by examiner]
US 20210074080A1 · Roberts · 2021 [cited by examiner]
US 20210182996A1 · Cella · 2021 [cited by examiner]
US 20220332331A1 · Ming · 2022 [cited by examiner]
WO 2017205961A1 · 2017 [cited by applicant]
International Search Report and Written Opinion for International Application No. PCT/US2019/068322, mailed Mar. 31, 2020, 8 pages. [cited by applicant]
Office Action for European Patent Application No. 19843003.5, mailed Oct. 1, 2021, 8 Pages. [cited by applicant]