IP Library › Granted Patent US 12,656,124
Granted Patent B2
US 12,656,124 · App. 18/471,685 · Granted Jun 16, 2026

Drone parcel delivery matrix-based safety determination

Inventors: Sarvesh S. Patel (Pune, IN); Gandhi Sivakumar (Mountain View, CA); Kushal S. Patel (Pune, IN)
Assignee: International Business Machines Corporation
G01C21/20B64U10/00B64U2101/64
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 12,656,124
App. No.
18/471,685
Granted
Jun 16, 2026
Kind
B2
Abstract

A computer-implemented method, a computer system, and a computer program product are provided. A first computer receives a message that indicates a destination location for a drone flight. The first computer generates a first recommendation for a route from a departure location to the destination location for the drone flight. The generating includes relying on a first safety matrix that represents a geographical area that includes the departure and destination locations. The first safety matrix includes rows and columns of numbers. Each number represents a first safety factor for a respective portion of a map that illustrates the geographical area. The generating also includes relying on a first analysis regarding a direct route between the departure and destination locations. The first analysis includes analyzing values of the first safety matrix along portions representing the direct route.

Claims (51)

1 . A computer-implemented method comprising:

receiving, via a first computer, a message indicating a destination location for a drone flight;

generating, via the first computer, a first recommendation for a route from a departure location to the destination location for the drone flight, wherein the generating comprises:

relying on multiple safety matrices representing a geographical area that includes the departure and destination locations, each safety matrix of the multiple safety matrices comprising respective rows and columns of numbers, each number representing a safety factor for a respective portion of a map that illustrates the geographical area, each of the multiple safety matrices representing a different vertical layer of a three-dimensional map;

relying on a first analysis regarding a direct route between the departure and destination locations, the first analysis includes analyzing values of the multiple safety matrices along portions representing the direct route;

wherein the route includes at least one change for an altitude of a drone flying in airspace, the at least one change for the altitude resulting in increased safety for the flight;

in response to the first analysis indicating that the direct route has a safety risk exceeding a threshold value, relying on alternative route comparison that uses a respective summation of values of the multiple safety matrices along additional portions representing alternative routes, respectively; and

selecting the first recommendation from the alternative routes based on the alternative route comparison, wherein the alternative route comparison weights a respective matrix value based on a respective length the respective alternative route passes through a map sub-region corresponding to a matrix position of the respective matrix value; and

transmitting the first recommendation and the route to the drone to control the drone for the drone flight along the route including along the at least one change.

2 . The computer-implemented method of claim 1 , wherein the alternative route comparison comprises applying a hill climbing algorithm to the first safety matrix.

3 . The computer-implemented method of claim 1 , wherein the multiple safety matrices are based on bird presence in the geographical area.

4 . The computer-implemented method of claim 3 , wherein the multiple safety matrices are based on bird sensing performed via one or more satellites.

5 . The computer-implemented method of claim 3 , wherein the multiple safety matrices are based on roads and on traffic conditions along the roads.

6 . The computer-implemented method of claim 1 , wherein each of the multiple safety matrices comprises a respective combined safety matrix being formed by combining a first safety matrix and a second safety matrix, each of the respective first and second safety matrices comprising rows and columns of numbers, each number representing a first safety factor for the respective portions of the map for the first safety matrices and a second safety factor for the respective portions of the map of the second safety matrices, the second safety factor being different from the first safety factor;

wherein the first analysis includes analyzing values of the combined safety matrices along the portions representing the direct route.

7 . The computer-implemented method of claim 6 , wherein the combining adds the values of the second safety matrix to values in corresponding positions of the first safety matrix for each respective portion of the map.

8 . The computer-implemented method of claim 6 , wherein the first safety matrix is based on bird presence in the geographical area and the second safety matrix is based on roads in the geographical area.

9 . The computer-implemented method of claim 6 , wherein the first analysis weights a respective matrix value based on a respective length the direct route passes through a map sub-region corresponding to a matrix position of the respective matrix value.

10 . The computer-implemented method of claim 1 , further comprising:

receiving temporal information about a desired time for the drone flight; and

selecting the first safety matrix from a stored library of sets of safety matrices based on the temporal information.

11 . The computer-implemented method of claim 1 , further comprising:

receiving parcel information about a parcel to be delivered via the drone flight; and

performing the first analysis further based on the parcel information.

12 . The computer-implemented method of claim 1 , wherein a number of the rows of each of the multiple safety matrices equals a number of latitudinal divisions on the map, and a number of the columns of each of the multiple safety matrices equals a number of longitudinal divisions on the map.

13 . The computer-implemented method of claim 1 , wherein the first analysis weights a respective matrix value based on a respective length the direct route passes through a map sub-region corresponding to a matrix position of the respective matrix value.

14 . A computer system comprising:

one or more processors, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors to cause the computer system to:

receive a message indicating a destination location for a drone flight;

generate a first recommendation for a route from a departure location to the destination location for the drone flight, wherein the generating comprises:

relying on multiple safety matrices representing a geographical area that includes the departure and destination locations, each safety matrix of the multiple safety matrices comprising respective rows and columns of numbers, each number representing a safety factor for a respective portion of a map that illustrates the geographical area, each of the multiple safety matrices representing a different vertical layer of a three-dimensional map;

relying on a first analysis regarding a direct route between the departure and destination locations, the first analysis includes analyzing values of the multiple safety matrices along portions representing the direct route;

wherein the route includes at least one change for an altitude of a drone flying in airspace, the at least one change for the altitude resulting in increased safety for the flight;

in response to the first analysis indicating that the direct route has a safety risk exceeding a threshold value, relying on alternative route comparison that uses a respective summation of values of the multiple safety matrices along additional portions representing alternative routes, respectively; and

selecting the first recommendation from the alternative routes based on the alternative route comparison, wherein the alternative route comparison weights a respective matrix value based on a respective length the respective alternative route passes through a map sub-region corresponding to a matrix position of the respective matrix value; and

transmitting the first recommendation and the route to the drone to control the drone for the drone flight along the route including along the at least one change.

15 . The computer system of claim 14 , wherein the alternative route comparison comprises applying a hill climbing algorithm to the multiple safety matrices.

16 . A computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions being executable by a computer to cause the computer to:

receive a message indicating a destination location for a drone flight;

generate a first recommendation for a route from a departure location to the destination location for the drone flight, wherein the generating comprises:

relying on multiple safety matrices representing a geographical area that includes the departure and destination locations, each safety matrix of the multiple safety matrices comprising respective rows and columns of numbers, each number representing a safety factor for a respective portion of a map that illustrates the geographical area, each of the multiple safety matrices representing a different vertical layer of a three-dimensional map;

relying on a first analysis regarding a direct route between the departure and destination locations, the first analysis includes analyzing values of the multiple safety matrices along portions representing the direct route;

wherein the route includes at least one change for an altitude of a drone flying in airspace, the at least one change for the altitude resulting in increased safety for the flight;

in response to the first analysis indicating that the direct route has a safety risk exceeding a threshold value, relying on alternative route comparison that uses a respective summation of values of the multiple safety matrices along additional portions representing alternative routes, respectively; and

selecting the first recommendation from the alternative routes based on the alternative route comparison, wherein the alternative route comparison weights a respective matrix value based on a respective length the respective alternative route passes through a map sub-region corresponding to a matrix position of the respective matrix value; and

transmitting the first recommendation and the route to the drone to control the drone for the drone flight along the route including along the at least one change.

17 . The computer program product of claim 16 , wherein the alternative route comparison comprises applying a hill climbing algorithm to the first safety matrix.

18 . The computer program product of claim 16 , wherein the multiple safety matrices are based on bird presence in the geographical area.

19 . The computer program product of claim 18 , wherein the multiple safety matrices are based on bird sensing performed via one or more satellites.

20 . The computer program product of claim 16 , wherein each of the multiple safety matrices comprises a respective combined safety matrix being formed by combining a first safety matrix and a second safety matrix, each of the respective first and second safety matrices comprising rows and columns of numbers, each number representing a first safety factor for the respective portions of the map for the first safety matrices and a second safety factor for the respective portions of the map of the second safety matrices, the second safety factor being different from the first safety factor;

wherein the first analysis includes analyzing values of the combined safety matrices along the portions representing the direct route.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 21, 2023
From: PATEL, SARVESH S.; SIVAKUMAR, GANDHI; PATEL, KUSHAL S.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 064984/0946 →
Continuity (1)
Related Publication 20250102305A1 · Mar 27, 2025
References Cited (16)
US 8570211B1 · Piesinger · 2013 [cited by examiner]
US 9494937B2 · Siegel · 2016 [cited by applicant]
US 9552736B2 · Taveira · 2017 [cited by applicant]
US 11726482B2 · Nigam · 2023 [cited by examiner]
US 20150242972A1 · Lemmey · 2015 [cited by applicant]
US 20160284221A1 · Hinkle · 2016 [cited by applicant]
US 20180300834A1 · High · 2018 [cited by examiner]
US 20210223777A1 · Nigam · 2021 [cited by examiner]
US 20210325907A1 · White · 2021 [cited by examiner]
US 20210390868A1 · Ratajczak · 2021 [cited by examiner]
US 20240257655A1 · Takemura · 2024 [cited by examiner]
CA 2956807A1 · 2016 [cited by applicant]
CN 106950985B · 2020 [cited by applicant]
CN 119668275A · 2025 [cited by applicant]
WO 2021255870A1 · 2021 [cited by applicant]
Disclosed Anonymously, “Method and System for Predicting and Recommending Drone Travel Routes based on Historical Data and Real-time Data Feeds,” IP.com Prior Art Database Technical Disclosure, IP.com No. IPCOM000241624… [cited by applicant]