Unmanned aerial vehicle maintenance troubleshooting decision tree

• US 10,399,706 B1
• Filed: 06/22/2016
• Issued: 09/03/2019
• Est. Priority Date: 06/22/2016
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Hanlon, Jon T., Sibon, Mark Daniel
• Primary Examiner(s): Boomer, Jeffrey C
• Application Number:
  US15/190,022
• Time in Patent Office: 1,168 Days
• CPC Class Codes: B64F 5/60 Testing or inspecting aircraft components or systems
• CPC Class Codes: B64U 2101/64 for parcel delivery or retrieval
• CPC Class Codes: G06F 8/65 Updates security arrangements therefor G06F21/57
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G07C 5/006 Indicating maintenance
• CPC Class Codes: G07C 5/008 communicating information to a remotely located station transmission systems for measured values G08C
• CPC Class Codes: G07C 5/0808 Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/0816 Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G07C 5/0841 Registering performance data recording measured values G01D; information storage G11B

Abstract

A maintenance notification for a UAV may be sent to a service provider. The service provider may identify the UAV, such as to access a profile associated with the UAV that includes at least hardware and software configurations for the UAV. The service provider may generate a customized maintenance decision tree to organize tasks to be performed for the specific UAV to determine a maintenance action to remedy a fault or problem associated with the maintenance notification. The decision tree may be formed using history of the UAV and information about other UAVs to construct the decision tree tailored to the specific UAV under analysis. At least some operations included in the decision tree may be automated. Traversal of the decision tree may lead to updates of the UAV of hardware, software, or both.

Claims

1. A method to maintain an unmanned aerial vehicle (UAV) in response to a fault message, the method comprising:

receiving the fault message from the UAV, wherein the fault message includes at least an identifier of the UAV;

determining a profile associated with the UAV based at least in part on the identifier, the profile including at least one of a flight history or a maintenance history associated with the UAV;

accessing data from the profile associated with the UAV that includes at least a hardware configuration and a software configuration of the UAV;

accessing maintenance data from at least one other UAV that has the hardware configuration or the software configuration;

designating a reliability rating to at least some of the maintenance data based at least in part on a source of the maintenance data, the source of the maintenance data associated with a location that the maintenance data is at least one of generated, collected, stored, or maintained;

allocating weights to the at least some of the maintenance data, based at least in part on the reliability rating, to modify an influence of the maintenance data when applied to the UAV;

determining available maintenance resources at a maintenance location;

creating a custom decision tree that organizes maintenance operations to be performed on the UAV associated with determining a maintenance action to perform on the UAV to resolve a fault associated with the fault message, the custom decision tree created based at least in part on the maintenance data, the weights, and the maintenance resources available at the maintenance location;

traversing the custom decision tree via an at least partially automated process to isolate the maintenance action to perform on the UAV;

determining the maintenance action to resolve the fault associated with the fault message; and

updating software of the UAV based at least in part on the maintenance action.

2. The method as recited in claim 1, wherein the determining the available maintenance resources further includes determining availability of at least one of (i) an automated software test device to test software operability on the UAV or (ii) a UAV test device to measure physical interaction with the UAV during a testing protocol to test hardware operability.

3. The method as recited in claim 1, wherein the custom decision tree specifies a timing of operations to be performed based at least in part on availability schedules of the maintenance resources at the maintenance location.

4. The method as recited in claim 1, wherein the custom decision tree includes at least one outlier maintenance action accessible via the custom decision tree, the outlier maintenance action being associated with a prior maintenance action performed on a different UAV having a second hardware configuration and a second software configuration, wherein the second hardware configuration is different than the hardware configuration and the second software configuration is different than the software configuration.

5. A maintenance system comprising:

one or more processors; and

memory to store computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising;

receiving a maintenance notification associated with an unmanned aerial vehicle (UAV), wherein the maintenance notification includes at least an identifier of the UAV;

determining a profile associated with the UAV based at least in part on the identifier, the profile including at least one of a flight history or a maintenance history associated with the UAV;

determining a hardware configuration and a software configuration of the UAV based at least in part on the profile;

accessing maintenance data from at least one other UAV having at least one of the hardware configuration or the software configuration;

designating a reliability rating to at least some of the maintenance data based at least in part on a source of the maintenance data, the source of the maintenance data associated with a location that the maintenance data is at least one of generated, collected, stored, or maintained;

determining one or more maintenance resources available at a maintenance location;

creating a decision tree that prioritizes one or more maintenance operations to be performed on the UAV, the decision tree created based at least in part on the reliability rating, the maintenance data, and the one or more maintenance resources available at the maintenance location; and

determining, by traversal of the decision tree, a maintenance action to resolve the maintenance notification, the maintenance action including at least an update to software executed by the UAV.

6. The maintenance system as recited in claim 5, wherein the acts further comprise:

determining weights to be applied to the at least some of the maintenance data, the weights based at least in part on the reliability rating; and

applying the weights to the at least some of the maintenance data during the creating of the decision tree.

7. The maintenance system as recited in claim 5, wherein the acts further comprise presenting the decision tree via a user interface (UI) that communicates at least progress of the traversal of the decision tree.

8. The maintenance system as recited in claim 5, wherein the decision tree includes at least one outlier maintenance action accessible via the decision tree, wherein the outlier maintenance action is associated with a lower statistical chance of being implemented via the decision tree relative to other maintenance actions.

9. The maintenance system as recited in claim 5, wherein the decision tree includes at least one outlier maintenance action accessible via the decision tree, and wherein the outlier maintenance action is associated with a lower sample size relative to other maintenance actions.

10. The maintenance system as recited in claim 5, wherein the decision tree includes at least one outlier maintenance action accessible via the decision tree, and wherein the outlier maintenance action is associated with a prior maintenance action performed on a different UAV having a second hardware configuration and a second software configuration, wherein the second hardware configuration is different than the hardware configuration and the second software configuration is different than the software configuration.

11. The maintenance system as recited in claim 5, wherein the determining the one or more maintenance resources available at the maintenance location further includes determining availability of at least one of (i) an automated software test device to test software operability on the UAV or (ii) a UAV test device to measure physical interaction with the UAV during a testing protocol to test hardware operability.

12. The maintenance system as recited in claim 5, wherein the decision tree specifies a timing of operations to be performed based at least in part on availability schedules of the one or more maintenance resources at the maintenance location.

13. The maintenance system as recited in claim 5, wherein the maintenance action includes installation of a substitute part on the UAV in lieu of a standard part, wherein the substitute part is different than the standard part in at least one of lifespan, size, mass, performance metrics, performance outputs, or physical attributes, and further comprising updating the software of the UAV based at least in part on use of the substitute part.

14. The maintenance system as recited in claim 5, wherein the maintenance notification is a fault message, and wherein the receiving the maintenance notification includes receiving at least one of log data or an indication of software code executing in association with occurrence of a fault associated with the fault message.

15. A method comprising:

receiving a maintenance notification associated with an unmanned aerial vehicle (UAV), wherein the maintenance notification includes at least an identifier of the UAV;

determining a profile associated with the UAV based at least in part on the identifier, the profile including at least one of a flight history or a maintenance history associated with the UAV;

determining a hardware configuration and a software configuration of the UAV, based at least in part on the profile;

accessing maintenance data (i) associated with the UAV and (ii) associated with at least one other UAV having at least one of the hardware configuration or the software configuration;

designating a reliability rating to at least some of the maintenance data based at least in part on a source of the maintenance data, the source of the maintenance data associated with a location that the maintenance data is at least one of generated, collected, stored, or maintained;

determining one or more available maintenance resources at a maintenance location;

creating a custom decision tree, based at least in part on the maintenance data, that prioritizes one or more maintenance operations to be performed on the UAV, the custom decision tree organized based at least in part on the reliability rating and the one or more maintenance resources available at the maintenance location;

determining, by traversal of the custom decision tree, a maintenance action to perform on the UAV to resolve the maintenance notification; and

causing an update to software executed by the UAV in response to determining the maintenance action.

16. The method as recited in claim 15, wherein the custom decision tree specifies a timing of operations to be performed based at least in part on availability schedules of the one or more maintenance resources at the maintenance location.

17. The method as recited in claim 15, wherein the custom decision tree includes at least one outlier maintenance action accessible via the custom decision tree, the outlier maintenance action based at least in part on a prior maintenance action performed on a different UAV having a second hardware configuration and a second software configuration, wherein the second hardware configuration is different than the hardware configuration and the second software configuration is different than the software configuration.

18. The method as recited in claim 15, further comprising:

receiving a signal from a test device that a maintenance operation specified in the custom decision tree has been completed; and

selecting at least one of a next maintenance operation or the maintenance action based at least in part on the traversal of the custom decision tree.

19. The method as recited in claim 15, further comprising presenting a user interface (UI) that graphically indicates at least progress of the traversal of the custom decision tree.

20. The method as recited in claim 15, wherein the maintenance action includes installation of a substitute part on the UAV in lieu of a standard part, wherein the substitute part is different than the standard part in at least one of lifespan, size, mass, performance metrics, performance outputs, or physical attributes, and further comprising upgrading the software of the UAV based at least in part on use of the substitute part.