FEEDBACK BASED SMART CLUSTERING MECHANISM FOR UNMANNED AERIAL VEHICLE ASSIGNMENT

• US 20200130828A1
• Filed: 10/26/2018
• Published: 04/30/2020
• Est. Priority Date: 10/26/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: PANDIT, Sushain, OBERHOFER, Martin, WANG, Fang, LIU, Su
• Granted Patent: US 11,046,431 B2
• Time in Patent Office: Days
• CPC Class Codes: B64C 39/024 of the remote controlled vehicle type, i.e. RPV
• CPC Class Codes: B64U 2101/60 for transporting passengers; for transporting goods other than weapons
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06Q 50/40 Business processes related to the transportation industry shipping G06Q10/083
• CPC Class Codes: G08G 5/0013 with a ground station
• CPC Class Codes: G08G 5/0026 located on the ground
• CPC Class Codes: G08G 5/0043 Traffic management of multiple aircrafts from the ground G08G5/003 takes precedence; data processing specially designed for resource management, e.g. scheduling or allocating time, human or machine resources G06Q10/06
• CPC Class Codes: G08G 5/0069 specially adapted for an unmanned aircraft
• CPC Class Codes: G08G 5/0091 for monitoring atmospheric conditions radar or analogous systems specially adapted for meteorological use G01S13/95; meteorology G01W

Abstract

A computer-implemented method includes generating, by a computer device, a plurality of clusters of unmanned aerial vehicles (UAVs) from a plurality of UAVs having different UAV characteristics, the clusters being generated based on the UAV characteristics of each of the UAVs; determining, by the computer device, task characteristics for a first task; selecting, by the computer device, one of the clusters based on the task characteristics of the first task; assigning to the first task, by the computer device, a first UAV of the plurality of UAVs from the selected cluster; receiving, by the computer device, task feedback regarding an attempt by the first UAV to complete the first task; and reassigning, by the computer device, and based on the task feedback, the first UAV to a determined one of the plurality of clusters.

Claims

1. A method comprising:

generating, by a computer device, a plurality of clusters of unmanned aerial vehicles (UAVs) from a plurality of UAVs having different UAV characteristics, the clusters being generated based on the UAV characteristics of each of the UAVs;

determining, by the computer device, task characteristics for a first task;

selecting, by the computer device, one of the clusters based on the task characteristics of the first task;

assigning to the first task, by the computer device, a first UAV of the plurality of UAVs from the selected cluster;

receiving, by the computer device, task feedback regarding an attempt by the first UAV to complete the first task; and

reassigning, by the computer device, and based on the task feedback, the first UAV to a determined one of the plurality of clusters.

2. The method of claim 1, wherein the clusters are established such that each cluster has a defined set of cluster parameters.

3. The method of claim 2, wherein the cluster parameters include a range of task distance and a UAV thrust/weight ratio.

4. The method of claim 2, wherein the generating is additionally based on seed data, the seed data being at least partially calculated from the UAV characteristics of a seed data set of UAVs that are a subset of the plurality of UAVs.

5. The method of claim 1, wherein the task feedback includes whether the first UAV successfully completed the first task.

6. The method of claim 5, wherein the task feedback includes a reason why the first UAV did not successfully complete the first task.

7. The method of claim 1, wherein the computer device receives the task feedback from the first UAV.

8. The method of claim 1, wherein the computer device receives the task feedback from a feedback analysis module.

9. The method of claim 8, wherein the feedback analysis module is located remotely from the computing device.

10. The method of claim 1, wherein a service provider provides a service, and the service is selected from the group consisting of creating, maintaining, deploying and supporting the computer device.

11. The method of claim 1, wherein the computer device and the UAVs are provided by a service provider on a subscription, advertising, and/or fee basis.

12. A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

generate a plurality of clusters of unmanned aerial vehicles (UAVs) from a plurality of UAVs, each of the clusters having a set of cluster parameters;

determine task characteristics for a first task;

select one of the clusters based on the task characteristics of the first task being within the cluster parameters of the selected cluster;

assign to the first task a first UAV of the plurality of UAVs from the selected cluster;

receive task feedback regarding an attempt by the first UAV to complete the task; and

reassign, based on the task feedback, the first UAV to a determined one of the plurality of clusters.

13. The computer program product of claim 12, the program instructions causing the generating by the computing device of the plurality of clusters to be based on UAV characteristics of each of the UAVs.

14. The computer program product of claim 13, the program instructions further causing the computing device to add a new UAV that is not one of the plurality of UAVs to one of the clusters based on UAV characteristics of the new UAV.

15. The computer program product of claim 14, the program instructions causing the computing device to revise the UAV characteristics of the first UAV based on the task feedback.

16. The computer program product of claim 15, the program instructions further causing the computing device to remove the first UAV from the cluster to which it is assigned based on revised UAV characteristics of the first UAV being outside of the cluster parameters of all of the clusters.

17. The computer program product of claim 13, the program instructions further causing the computing device to generate the plurality of clusters using a k-means clustering algorithm.

18. A system comprising:

a processor, a computer readable memory, and a computer readable storage medium;

program instructions to generating, by a computer device, a plurality of original clusters of unmanned aerial vehicles (UAVs) from a plurality of UAVs having different UAV characteristics, the original clusters being generated based on the UAV characteristics of each of the UAVs, each of the original clusters having a set of cluster parameters;

program instructions to select one of the original clusters based on task characteristics of a first task being within the cluster parameters of the selected original cluster;

program instructions to assign to the first task a first UAV of the plurality of UAVs from the selected original cluster;

program instructions to receive task feedback regarding an attempt by the first UAV to complete the task;

program instructions to reassign, based on the task feedback, the first UAV to a determined one of the plurality of clusters; and

program instructions to generate a plurality of new clusters of UAVs from the plurality of UAVs,

wherein the program instructions are stored on the computer readable storage medium for execution by the processor via the computer readable memory.

19. The system of claim 18, wherein the program instructions to generate a plurality of new clusters include combining two of the original clusters into one of the new clusters.

20. The system of claim 18, wherein at least one of the new clusters has cluster parameters that are different than cluster parameters of all of the original clusters.