US 12,307,908 B2
Drone deployment for distributed asset maintenance and repair
Thiago Bianchi, São Carlos (BR); Tiago Bertoni Scarton, São Paulo (BR); Raghu Kiran Ganti, White Plains, NY (US); and Mudhakar Srivatsa, White Plains, NY (US)
Assigned to INTERNATIONAL BUSINESSCORPORATION, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Feb. 8, 2022, as Appl. No. 17/667,389.
Prior Publication US 2023/0252902 A1, Aug. 10, 2023
Int. Cl. G08G 5/32 (2025.01); G06N 3/084 (2023.01); G06Q 10/20 (2023.01); G06Q 30/04 (2012.01); G08G 5/34 (2025.01); G08G 5/55 (2025.01); G08G 5/57 (2025.01); G08G 5/72 (2025.01); G08G 5/76 (2025.01)
CPC G08G 5/32 (2025.01) [G06N 3/084 (2013.01); G06Q 10/20 (2013.01); G06Q 30/04 (2013.01); G08G 5/34 (2025.01); G08G 5/55 (2025.01); G08G 5/57 (2025.01); G08G 5/723 (2025.01); G08G 5/76 (2025.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising operations for:
identifying a fix for a problem at an asset of a plurality of assets;
identifying a drone of a plurality of drones to perform the fix;
generating an initial flight plan that describes a drone flight path for the drone from a current location to a location of the asset;
obtaining, from one or more edge devices, real-time data that includes real-time air traffic data, real-time road traffic data, and real-time drone flight path conditions;
generating an updated flight plan for the drone by updating the drone flight path using the real-time air traffic data, the real-time road traffic data, and the real-time drone flight path conditions;
predicting, using a machine learning model, a cost and a period of time for the updated drone flight path;
generating an overall flight plan with a particular drone flight path for the drone and drone flight paths for one or more other drones using the predicted cost and the predicted period of time;
sending the particular drone flight path from the overall flight plan to the drone with instructions to fix the problem; and
in response to receiving a status from the drone of the problem being fixed,
computing an actual cost and an actual period of time for the drone flight path based on the status; and
updating the machine learning model with the actual cost and the actual period of time.